vendor: OpenCV 5.0.0 snapshot at 755e50675d97db9b7d449d8bd6b09888646f6c6e

modules/xobjdetect/samples/dbt_face_detection.cpp

@@ -0,0 +1,111 @@
+#if defined(__linux__) || defined(LINUX) || defined(__APPLE__) || defined(ANDROID) || (defined(_MSC_VER) && _MSC_VER>=1800)
+
+#include <opencv2/imgproc.hpp>  // Gaussian Blur
+#include <opencv2/core.hpp>        // Basic OpenCV structures (cv::Mat, Scalar)
+#include <opencv2/videoio.hpp>
+#include <opencv2/highgui.hpp>  // OpenCV window I/O
+#include <opencv2/features.hpp>
+#include <opencv2/xobjdetect.hpp>
+
+#include <stdio.h>
+
+using namespace std;
+using namespace cv;
+
+const string WindowName = "Face Detection example";
+
+class CascadeDetectorAdapter: public DetectionBasedTracker::IDetector
+{
+    public:
+        CascadeDetectorAdapter(cv::Ptr<cv::CascadeClassifier> detector):
+            IDetector(),
+            Detector(detector)
+        {
+            CV_Assert(detector);
+        }
+
+        void detect(const cv::Mat &Image, std::vector<cv::Rect> &objects) CV_OVERRIDE
+        {
+            Detector->detectMultiScale(Image, objects, scaleFactor, minNeighbours, 0, minObjSize, maxObjSize);
+        }
+
+        virtual ~CascadeDetectorAdapter() CV_OVERRIDE
+        {}
+
+    private:
+        CascadeDetectorAdapter();
+        cv::Ptr<cv::CascadeClassifier> Detector;
+ };
+
+int main(int , char** )
+{
+    namedWindow(WindowName);
+
+    VideoCapture VideoStream(0);
+
+    if (!VideoStream.isOpened())
+    {
+        printf("Error: Cannot open video stream from camera\n");
+        return 1;
+    }
+
+    std::string cascadeFrontalfilename = samples::findFile("data/lbpcascades/lbpcascade_frontalface.xml");
+    cv::Ptr<cv::CascadeClassifier> cascade = makePtr<cv::CascadeClassifier>(cascadeFrontalfilename);
+    cv::Ptr<DetectionBasedTracker::IDetector> MainDetector = makePtr<CascadeDetectorAdapter>(cascade);
+    if ( cascade->empty() )
+    {
+      printf("Error: Cannot load %s\n", cascadeFrontalfilename.c_str());
+      return 2;
+    }
+
+    cascade = makePtr<cv::CascadeClassifier>(cascadeFrontalfilename);
+    cv::Ptr<DetectionBasedTracker::IDetector> TrackingDetector = makePtr<CascadeDetectorAdapter>(cascade);
+    if ( cascade->empty() )
+    {
+      printf("Error: Cannot load %s\n", cascadeFrontalfilename.c_str());
+      return 2;
+    }
+
+    DetectionBasedTracker::Parameters params;
+    DetectionBasedTracker Detector(MainDetector, TrackingDetector, params);
+
+    if (!Detector.run())
+    {
+        printf("Error: Detector initialization failed\n");
+        return 2;
+    }
+
+    Mat ReferenceFrame;
+    Mat GrayFrame;
+    vector<Rect> Faces;
+
+    do
+    {
+        VideoStream >> ReferenceFrame;
+        cvtColor(ReferenceFrame, GrayFrame, COLOR_BGR2GRAY);
+        Detector.process(GrayFrame);
+        Detector.getObjects(Faces);
+
+        for (size_t i = 0; i < Faces.size(); i++)
+        {
+            rectangle(ReferenceFrame, Faces[i], Scalar(0,255,0));
+        }
+
+        imshow(WindowName, ReferenceFrame);
+    } while (waitKey(30) < 0);
+
+    Detector.stop();
+
+    return 0;
+}
+
+#else
+
+#include <stdio.h>
+int main()
+{
+    printf("This sample works for UNIX or ANDROID or Visual Studio 2013+ only\n");
+    return 0;
+}
+
+#endif

modules/xobjdetect/samples/facedetect.cpp

@@ -0,0 +1,257 @@
+#include "opencv2/xobjdetect.hpp"
+#include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
+#include "opencv2/videoio.hpp"
+#include <iostream>
+
+using namespace std;
+using namespace cv;
+
+static void help(const char** argv)
+{
+    cout << "\nThis program demonstrates the use of cv::CascadeClassifier class to detect objects (Face + eyes). You can use Haar or LBP features.\n"
+            "This classifier can recognize many kinds of rigid objects, once the appropriate classifier is trained.\n"
+            "It's most known use is for faces.\n"
+            "Usage:\n"
+        <<  argv[0]
+        <<  "   [--cascade=<cascade_path> this is the primary trained classifier such as frontal face]\n"
+            "   [--nested-cascade[=nested_cascade_path this an optional secondary classifier such as eyes]]\n"
+            "   [--scale=<image scale greater or equal to 1, try 1.3 for example>]\n"
+            "   [--try-flip]\n"
+            "   [filename|camera_index]\n\n"
+            "example:\n"
+        <<  argv[0]
+        <<  " --cascade=\"data/haarcascades/haarcascade_frontalface_alt.xml\" --nested-cascade=\"data/haarcascades/haarcascade_eye_tree_eyeglasses.xml\" --scale=1.3\n\n"
+            "During execution:\n\tHit any key to quit.\n"
+            "\tUsing OpenCV version " << CV_VERSION << "\n" << endl;
+}
+
+void detectAndDraw( Mat& img, CascadeClassifier& cascade,
+                    CascadeClassifier& nestedCascade,
+                    double scale, bool tryflip );
+
+string cascadeName;
+string nestedCascadeName;
+
+int main( int argc, const char** argv )
+{
+    VideoCapture capture;
+    Mat frame, image;
+    string inputName;
+    bool tryflip;
+    CascadeClassifier cascade, nestedCascade;
+    double scale;
+
+    cv::CommandLineParser parser(argc, argv,
+        "{help h||}"
+        "{cascade|data/haarcascades/haarcascade_frontalface_alt.xml|}"
+        "{nested-cascade|data/haarcascades/haarcascade_eye_tree_eyeglasses.xml|}"
+        "{scale|1|}{try-flip||}{@filename||}"
+    );
+    if (parser.has("help"))
+    {
+        help(argv);
+        return 0;
+    }
+    cascadeName = parser.get<string>("cascade");
+    nestedCascadeName = parser.get<string>("nested-cascade");
+    scale = parser.get<double>("scale");
+    if (scale < 1)
+        scale = 1;
+    tryflip = parser.has("try-flip");
+    inputName = parser.get<string>("@filename");
+    if (!parser.check())
+    {
+        parser.printErrors();
+        return 0;
+    }
+    if (!nestedCascade.load(samples::findFileOrKeep(nestedCascadeName)))
+        cerr << "WARNING: Could not load classifier cascade for nested objects" << endl;
+    if (!cascade.load(samples::findFile(cascadeName)))
+    {
+        cerr << "ERROR: Could not load classifier cascade" << endl;
+        help(argv);
+        return -1;
+    }
+    if( inputName.empty() || (isdigit(inputName[0]) && inputName.size() == 1) )
+    {
+        int camera = inputName.empty() ? 0 : inputName[0] - '0';
+        if(!capture.open(camera))
+        {
+            cout << "Capture from camera #" <<  camera << " didn't work" << endl;
+            return 1;
+        }
+    }
+    else if (!inputName.empty())
+    {
+        image = imread(samples::findFileOrKeep(inputName), IMREAD_COLOR);
+        if (image.empty())
+        {
+            if (!capture.open(samples::findFileOrKeep(inputName)))
+            {
+                cout << "Could not read " << inputName << endl;
+                return 1;
+            }
+        }
+    }
+    else
+    {
+        image = imread(samples::findFile("lena.jpg"), IMREAD_COLOR);
+        if (image.empty())
+        {
+            cout << "Couldn't read lena.jpg" << endl;
+            return 1;
+        }
+    }
+
+    if( capture.isOpened() )
+    {
+        cout << "Video capturing has been started ..." << endl;
+
+        for(;;)
+        {
+            capture >> frame;
+            if( frame.empty() )
+                break;
+
+            Mat frame1 = frame.clone();
+            detectAndDraw( frame1, cascade, nestedCascade, scale, tryflip );
+
+            char c = (char)waitKey(10);
+            if( c == 27 || c == 'q' || c == 'Q' )
+                break;
+        }
+    }
+    else
+    {
+        cout << "Detecting face(s) in " << inputName << endl;
+        if( !image.empty() )
+        {
+            detectAndDraw( image, cascade, nestedCascade, scale, tryflip );
+            waitKey(0);
+        }
+        else if( !inputName.empty() )
+        {
+            /* assume it is a text file containing the
+            list of the image filenames to be processed - one per line */
+            FILE* f = fopen( inputName.c_str(), "rt" );
+            if( f )
+            {
+                char buf[1000+1];
+                while( fgets( buf, 1000, f ) )
+                {
+                    int len = (int)strlen(buf);
+                    while( len > 0 && isspace(buf[len-1]) )
+                        len--;
+                    buf[len] = '\0';
+                    cout << "file " << buf << endl;
+                    image = imread( buf, IMREAD_COLOR );
+                    if( !image.empty() )
+                    {
+                        detectAndDraw( image, cascade, nestedCascade, scale, tryflip );
+                        char c = (char)waitKey(0);
+                        if( c == 27 || c == 'q' || c == 'Q' )
+                            break;
+                    }
+                    else
+                    {
+                        cerr << "Aw snap, couldn't read image " << buf << endl;
+                    }
+                }
+                fclose(f);
+            }
+        }
+    }
+
+    return 0;
+}
+
+void detectAndDraw( Mat& img, CascadeClassifier& cascade,
+                    CascadeClassifier& nestedCascade,
+                    double scale, bool tryflip )
+{
+    double t = 0;
+    vector<Rect> faces, faces2;
+    const static Scalar colors[] =
+    {
+        Scalar(255,0,0),
+        Scalar(255,128,0),
+        Scalar(255,255,0),
+        Scalar(0,255,0),
+        Scalar(0,128,255),
+        Scalar(0,255,255),
+        Scalar(0,0,255),
+        Scalar(255,0,255)
+    };
+    Mat gray, smallImg;
+
+    cvtColor( img, gray, COLOR_BGR2GRAY );
+    double fx = 1 / scale;
+    resize( gray, smallImg, Size(), fx, fx, INTER_LINEAR_EXACT );
+    equalizeHist( smallImg, smallImg );
+
+    t = (double)getTickCount();
+    cascade.detectMultiScale( smallImg, faces,
+        1.1, 2, 0
+        //|CASCADE_FIND_BIGGEST_OBJECT
+        //|CASCADE_DO_ROUGH_SEARCH
+        |CASCADE_SCALE_IMAGE,
+        Size(30, 30) );
+    if( tryflip )
+    {
+        flip(smallImg, smallImg, 1);
+        cascade.detectMultiScale( smallImg, faces2,
+                                 1.1, 2, 0
+                                 //|CASCADE_FIND_BIGGEST_OBJECT
+                                 //|CASCADE_DO_ROUGH_SEARCH
+                                 |CASCADE_SCALE_IMAGE,
+                                 Size(30, 30) );
+        for( vector<Rect>::const_iterator r = faces2.begin(); r != faces2.end(); ++r )
+        {
+            faces.push_back(Rect(smallImg.cols - r->x - r->width, r->y, r->width, r->height));
+        }
+    }
+    t = (double)getTickCount() - t;
+    printf( "detection time = %g ms\n", t*1000/getTickFrequency());
+    for ( size_t i = 0; i < faces.size(); i++ )
+    {
+        Rect r = faces[i];
+        Mat smallImgROI;
+        vector<Rect> nestedObjects;
+        Point center;
+        Scalar color = colors[i%8];
+        int radius;
+
+        double aspect_ratio = (double)r.width/r.height;
+        if( 0.75 < aspect_ratio && aspect_ratio < 1.3 )
+        {
+            center.x = cvRound((r.x + r.width*0.5)*scale);
+            center.y = cvRound((r.y + r.height*0.5)*scale);
+            radius = cvRound((r.width + r.height)*0.25*scale);
+            circle( img, center, radius, color, 3, 8, 0 );
+        }
+        else
+            rectangle( img, Point(cvRound(r.x*scale), cvRound(r.y*scale)),
+                       Point(cvRound((r.x + r.width-1)*scale), cvRound((r.y + r.height-1)*scale)),
+                       color, 3, 8, 0);
+        if( nestedCascade.empty() )
+            continue;
+        smallImgROI = smallImg( r );
+        nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
+            1.1, 2, 0
+            //|CASCADE_FIND_BIGGEST_OBJECT
+            //|CASCADE_DO_ROUGH_SEARCH
+            //|CASCADE_DO_CANNY_PRUNING
+            |CASCADE_SCALE_IMAGE,
+            Size(30, 30) );
+        for ( size_t j = 0; j < nestedObjects.size(); j++ )
+        {
+            Rect nr = nestedObjects[j];
+            center.x = cvRound((r.x + nr.x + nr.width*0.5)*scale);
+            center.y = cvRound((r.y + nr.y + nr.height*0.5)*scale);
+            radius = cvRound((nr.width + nr.height)*0.25*scale);
+            circle( img, center, radius, color, 3, 8, 0 );
+        }
+    }
+    imshow( "result", img );
+}

modules/xobjdetect/samples/facial_features.cpp

@@ -0,0 +1,215 @@
+/*
+ * Author: Samyak Datta (datta[dot]samyak[at]gmail.com)
+ *
+ * A program to detect facial feature points using
+ * Haarcascade classifiers for face, eyes, nose and mouth
+ *
+ */
+
+#include "opencv2/xobjdetect.hpp"
+#include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
+
+#include <iostream>
+#include <cstdio>
+#include <vector>
+#include <algorithm>
+
+using namespace std;
+using namespace cv;
+
+// Functions for facial feature detection
+static void help(char** argv);
+static void detectFaces(Mat&, vector<Rect_<int> >&, string);
+static void detectEyes(Mat&, vector<Rect_<int> >&, string);
+static void detectNose(Mat&, vector<Rect_<int> >&, string);
+static void detectMouth(Mat&, vector<Rect_<int> >&, string);
+static void detectFacialFeaures(Mat&, const vector<Rect_<int> >, string, string, string);
+
+string input_image_path;
+string face_cascade_path, eye_cascade_path, nose_cascade_path, mouth_cascade_path;
+
+int main(int argc, char** argv)
+{
+    cv::CommandLineParser parser(argc, argv,
+            "{eyes||}{nose||}{mouth||}{help h||}{@image||}{@facexml||}");
+    if (parser.has("help"))
+    {
+        help(argv);
+        return 0;
+    }
+    input_image_path = parser.get<string>("@image");
+    face_cascade_path = parser.get<string>("@facexml");
+    eye_cascade_path = parser.has("eyes") ? parser.get<string>("eyes") : "";
+    nose_cascade_path = parser.has("nose") ? parser.get<string>("nose") : "";
+    mouth_cascade_path = parser.has("mouth") ? parser.get<string>("mouth") : "";
+    if (input_image_path.empty() || face_cascade_path.empty())
+    {
+        cout << "IMAGE or FACE_CASCADE are not specified";
+        return 1;
+    }
+    // Load image and cascade classifier files
+    Mat image;
+    image = imread(samples::findFile(input_image_path));
+
+    // Detect faces and facial features
+    vector<Rect_<int> > faces;
+    detectFaces(image, faces, face_cascade_path);
+    detectFacialFeaures(image, faces, eye_cascade_path, nose_cascade_path, mouth_cascade_path);
+
+    imshow("Result", image);
+
+    waitKey(0);
+    return 0;
+}
+
+static void help(char** argv)
+{
+    cout << "\nThis file demonstrates facial feature points detection using Haarcascade classifiers.\n"
+        "The program detects a face and eyes, nose and mouth inside the face."
+        "The code has been tested on the Japanese Female Facial Expression (JAFFE) database and found"
+        "to give reasonably accurate results. \n";
+
+    cout << "\nUSAGE: " << argv[0] << " [IMAGE] [FACE_CASCADE] [OPTIONS]\n"
+        "IMAGE\n\tPath to the image of a face taken as input.\n"
+        "FACE_CASCSDE\n\t Path to a haarcascade classifier for face detection.\n"
+        "OPTIONS: \nThere are 3 options available which are described in detail. There must be a "
+        "space between the option and it's argument (All three options accept arguments).\n"
+        "\t-eyes=<eyes_cascade> : Specify the haarcascade classifier for eye detection.\n"
+        "\t-nose=<nose_cascade> : Specify the haarcascade classifier for nose detection.\n"
+        "\t-mouth=<mouth-cascade> : Specify the haarcascade classifier for mouth detection.\n";
+
+
+    cout << "EXAMPLE:\n"
+        "(1) " << argv[0] << " image.jpg face.xml -eyes=eyes.xml -mouth=mouth.xml\n"
+        "\tThis will detect the face, eyes and mouth in image.jpg.\n"
+        "(2) " << argv[0] << " image.jpg face.xml -nose=nose.xml\n"
+        "\tThis will detect the face and nose in image.jpg.\n"
+        "(3) " << argv[0] << " image.jpg face.xml\n"
+        "\tThis will detect only the face in image.jpg.\n";
+
+    cout << " \n\nThe classifiers for face and eyes can be downloaded from : "
+        " \nhttps://github.com/opencv/opencv/tree/5.x/data/haarcascades";
+
+    cout << "\n\nThe classifiers for nose and mouth can be downloaded from : "
+        " \nhttps://github.com/opencv/opencv_contrib/tree/5.x/modules/face/data/cascades\n";
+}
+
+static void detectFaces(Mat& img, vector<Rect_<int> >& faces, string cascade_path)
+{
+    CascadeClassifier face_cascade;
+    face_cascade.load(samples::findFile(cascade_path));
+
+    if (!face_cascade.empty())
+        face_cascade.detectMultiScale(img, faces, 1.15, 3, 0|CASCADE_SCALE_IMAGE, Size(30, 30));
+    return;
+}
+
+static void detectFacialFeaures(Mat& img, const vector<Rect_<int> > faces, string eye_cascade,
+        string nose_cascade, string mouth_cascade)
+{
+    for(unsigned int i = 0; i < faces.size(); ++i)
+    {
+        // Mark the bounding box enclosing the face
+        Rect face = faces[i];
+        rectangle(img, Point(face.x, face.y), Point(face.x+face.width, face.y+face.height),
+                Scalar(255, 0, 0), 1, 4);
+
+        // Eyes, nose and mouth will be detected inside the face (region of interest)
+        Mat ROI = img(Rect(face.x, face.y, face.width, face.height));
+
+        // Check if all features (eyes, nose and mouth) are being detected
+        bool is_full_detection = false;
+        if( (!eye_cascade.empty()) && (!nose_cascade.empty()) && (!mouth_cascade.empty()) )
+            is_full_detection = true;
+
+        // Detect eyes if classifier provided by the user
+        if(!eye_cascade.empty())
+        {
+            vector<Rect_<int> > eyes;
+            detectEyes(ROI, eyes, eye_cascade);
+
+            // Mark points corresponding to the centre of the eyes
+            for(unsigned int j = 0; j < eyes.size(); ++j)
+            {
+                Rect e = eyes[j];
+                circle(ROI, Point(e.x+e.width/2, e.y+e.height/2), 3, Scalar(0, 255, 0), -1, 8);
+                /* rectangle(ROI, Point(e.x, e.y), Point(e.x+e.width, e.y+e.height),
+                    Scalar(0, 255, 0), 1, 4); */
+            }
+        }
+
+        // Detect nose if classifier provided by the user
+        double nose_center_height = 0.0;
+        if(!nose_cascade.empty())
+        {
+            vector<Rect_<int> > nose;
+            detectNose(ROI, nose, nose_cascade);
+
+            // Mark points corresponding to the centre (tip) of the nose
+            for(unsigned int j = 0; j < nose.size(); ++j)
+            {
+                Rect n = nose[j];
+                circle(ROI, Point(n.x+n.width/2, n.y+n.height/2), 3, Scalar(0, 255, 0), -1, 8);
+                nose_center_height = (n.y + n.height/2);
+            }
+        }
+
+        // Detect mouth if classifier provided by the user
+        double mouth_center_height = 0.0;
+        if(!mouth_cascade.empty())
+        {
+            vector<Rect_<int> > mouth;
+            detectMouth(ROI, mouth, mouth_cascade);
+
+            for(unsigned int j = 0; j < mouth.size(); ++j)
+            {
+                Rect m = mouth[j];
+                mouth_center_height = (m.y + m.height/2);
+
+                // The mouth should lie below the nose
+                if( (is_full_detection) && (mouth_center_height > nose_center_height) )
+                {
+                    rectangle(ROI, Point(m.x, m.y), Point(m.x+m.width, m.y+m.height), Scalar(0, 255, 0), 1, 4);
+                }
+                else if( (is_full_detection) && (mouth_center_height <= nose_center_height) )
+                    continue;
+                else
+                    rectangle(ROI, Point(m.x, m.y), Point(m.x+m.width, m.y+m.height), Scalar(0, 255, 0), 1, 4);
+            }
+        }
+
+    }
+
+    return;
+}
+
+static void detectEyes(Mat& img, vector<Rect_<int> >& eyes, string cascade_path)
+{
+    CascadeClassifier eyes_cascade;
+    eyes_cascade.load(samples::findFile(cascade_path, !cascade_path.empty()));
+
+    if (!eyes_cascade.empty())
+        eyes_cascade.detectMultiScale(img, eyes, 1.20, 5, 0|CASCADE_SCALE_IMAGE, Size(30, 30));
+    return;
+}
+
+static void detectNose(Mat& img, vector<Rect_<int> >& nose, string cascade_path)
+{
+    CascadeClassifier nose_cascade;
+    nose_cascade.load(samples::findFile(cascade_path, !cascade_path.empty()));
+
+    if (!nose_cascade.empty())
+        nose_cascade.detectMultiScale(img, nose, 1.20, 5, 0|CASCADE_SCALE_IMAGE, Size(30, 30));
+    return;
+}
+
+static void detectMouth(Mat& img, vector<Rect_<int> >& mouth, string cascade_path)
+{
+    CascadeClassifier mouth_cascade;
+    mouth_cascade.load(samples::findFile(cascade_path, !cascade_path.empty()));
+
+    if (!mouth_cascade.empty())
+        mouth_cascade.detectMultiScale(img, mouth, 1.20, 5, 0|CASCADE_SCALE_IMAGE, Size(30, 30));
+    return;
+}

modules/xobjdetect/samples/gpu/cascadeclassifier.cpp

@@ -0,0 +1,316 @@
+// WARNING: this sample is under construction! Use it on your own risk.
+#if defined _MSC_VER && _MSC_VER >= 1400
+#pragma warning(disable : 4100)
+#endif
+
+
+#include <iostream>
+#include <iomanip>
+#include "opencv2/xobjdetect.hpp"
+#include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
+#include "opencv2/cudaobjdetect.hpp"
+#include "opencv2/cudaimgproc.hpp"
+#include "opencv2/cudawarping.hpp"
+
+using namespace std;
+using namespace cv;
+using namespace cv::cuda;
+
+
+static void help()
+{
+    cout << "Usage: ./cascadeclassifier \n\t--cascade <cascade_file>\n\t(<image>|--video <video>|--camera <camera_id>)\n"
+            "Using OpenCV version " << CV_VERSION << endl << endl;
+}
+
+
+static void convertAndResize(const Mat& src, Mat& gray, Mat& resized, double scale)
+{
+    if (src.channels() == 3)
+    {
+        cv::cvtColor( src, gray, COLOR_BGR2GRAY );
+    }
+    else
+    {
+        gray = src;
+    }
+
+    Size sz(cvRound(gray.cols * scale), cvRound(gray.rows * scale));
+
+    if (scale != 1)
+    {
+        cv::resize(gray, resized, sz);
+    }
+    else
+    {
+        resized = gray;
+    }
+}
+
+static void convertAndResize(const GpuMat& src, GpuMat& gray, GpuMat& resized, double scale)
+{
+    if (src.channels() == 3)
+    {
+        cv::cuda::cvtColor( src, gray, COLOR_BGR2GRAY );
+    }
+    else
+    {
+        gray = src;
+    }
+
+    Size sz(cvRound(gray.cols * scale), cvRound(gray.rows * scale));
+
+    if (scale != 1)
+    {
+        cv::cuda::resize(gray, resized, sz);
+    }
+    else
+    {
+        resized = gray;
+    }
+}
+
+
+static void matPrint(Mat &img, int lineOffsY, Scalar fontColor, const string &ss)
+{
+    int fontFace = FONT_HERSHEY_DUPLEX;
+    double fontScale = 0.8;
+    int fontThickness = 2;
+    Size fontSize = cv::getTextSize("T[]", fontFace, fontScale, fontThickness, 0);
+
+    Point org;
+    org.x = 1;
+    org.y = 3 * fontSize.height * (lineOffsY + 1) / 2;
+    putText(img, ss, org, fontFace, fontScale, Scalar(0,0,0), 5*fontThickness/2, 16);
+    putText(img, ss, org, fontFace, fontScale, fontColor, fontThickness, 16);
+}
+
+
+static void displayState(Mat &canvas, bool bHelp, bool bGpu, bool bLargestFace, bool bFilter, double fps)
+{
+    Scalar fontColorRed = Scalar(255,0,0);
+    Scalar fontColorNV  = Scalar(118,185,0);
+
+    ostringstream ss;
+    ss << "FPS = " << setprecision(1) << fixed << fps;
+    matPrint(canvas, 0, fontColorRed, ss.str());
+    ss.str("");
+    ss << "[" << canvas.cols << "x" << canvas.rows << "], " <<
+        (bGpu ? "GPU, " : "CPU, ") <<
+        (bLargestFace ? "OneFace, " : "MultiFace, ") <<
+        (bFilter ? "Filter:ON" : "Filter:OFF");
+    matPrint(canvas, 1, fontColorRed, ss.str());
+
+    // by Anatoly. MacOS fix. ostringstream(const string&) is a private
+    // matPrint(canvas, 2, fontColorNV, ostringstream("Space - switch GPU / CPU"));
+    if (bHelp)
+    {
+        matPrint(canvas, 2, fontColorNV, "Space - switch GPU / CPU");
+        matPrint(canvas, 3, fontColorNV, "M - switch OneFace / MultiFace");
+        matPrint(canvas, 4, fontColorNV, "F - toggle rectangles Filter");
+        matPrint(canvas, 5, fontColorNV, "H - toggle hotkeys help");
+        matPrint(canvas, 6, fontColorNV, "1/Q - increase/decrease scale");
+    }
+    else
+    {
+        matPrint(canvas, 2, fontColorNV, "H - toggle hotkeys help");
+    }
+}
+
+
+int main(int argc, const char *argv[])
+{
+    if (argc == 1)
+    {
+        help();
+        return -1;
+    }
+
+    if (getCudaEnabledDeviceCount() == 0)
+    {
+        return cerr << "No GPU found or the library is compiled without CUDA support" << endl, -1;
+    }
+
+    cv::cuda::printShortCudaDeviceInfo(cv::cuda::getDevice());
+
+    string cascadeName;
+    string inputName;
+    bool isInputImage = false;
+    bool isInputVideo = false;
+    bool isInputCamera = false;
+
+    for (int i = 1; i < argc; ++i)
+    {
+        if (string(argv[i]) == "--cascade")
+            cascadeName = argv[++i];
+        else if (string(argv[i]) == "--video")
+        {
+            inputName = argv[++i];
+            isInputVideo = true;
+        }
+        else if (string(argv[i]) == "--camera")
+        {
+            inputName = argv[++i];
+            isInputCamera = true;
+        }
+        else if (string(argv[i]) == "--help")
+        {
+            help();
+            return -1;
+        }
+        else if (!isInputImage)
+        {
+            inputName = argv[i];
+            isInputImage = true;
+        }
+        else
+        {
+            cout << "Unknown key: " << argv[i] << endl;
+            return -1;
+        }
+    }
+
+    Ptr<cuda::CascadeClassifier> cascade_gpu = cuda::CascadeClassifier::create(cascadeName);
+
+    cv::CascadeClassifier cascade_cpu;
+    if (!cascade_cpu.load(cascadeName))
+    {
+        return cerr << "ERROR: Could not load cascade classifier \"" << cascadeName << "\"" << endl, help(), -1;
+    }
+
+    VideoCapture capture;
+    Mat image;
+
+    if (isInputImage)
+    {
+        image = imread(inputName);
+        CV_Assert(!image.empty());
+    }
+    else if (isInputVideo)
+    {
+        capture.open(inputName);
+        CV_Assert(capture.isOpened());
+    }
+    else
+    {
+        capture.open(atoi(inputName.c_str()));
+        CV_Assert(capture.isOpened());
+    }
+
+    namedWindow("result", 1);
+
+    Mat frame, frame_cpu, gray_cpu, resized_cpu, frameDisp;
+    vector<Rect> faces;
+
+    GpuMat frame_gpu, gray_gpu, resized_gpu, facesBuf_gpu;
+
+    /* parameters */
+    bool useGPU = true;
+    double scaleFactor = 1.0;
+    bool findLargestObject = false;
+    bool filterRects = true;
+    bool helpScreen = false;
+
+    for (;;)
+    {
+        if (isInputCamera || isInputVideo)
+        {
+            capture >> frame;
+            if (frame.empty())
+            {
+                break;
+            }
+        }
+
+        (image.empty() ? frame : image).copyTo(frame_cpu);
+        frame_gpu.upload(image.empty() ? frame : image);
+
+        convertAndResize(frame_gpu, gray_gpu, resized_gpu, scaleFactor);
+        convertAndResize(frame_cpu, gray_cpu, resized_cpu, scaleFactor);
+
+        TickMeter tm;
+        tm.start();
+
+        if (useGPU)
+        {
+            cascade_gpu->setFindLargestObject(findLargestObject);
+            cascade_gpu->setScaleFactor(1.2);
+            cascade_gpu->setMinNeighbors((filterRects || findLargestObject) ? 4 : 0);
+
+            cascade_gpu->detectMultiScale(resized_gpu, facesBuf_gpu);
+            cascade_gpu->convert(facesBuf_gpu, faces);
+        }
+        else
+        {
+            Size minSize = cascade_gpu->getClassifierSize();
+            cascade_cpu.detectMultiScale(resized_cpu, faces, 1.2,
+                                         (filterRects || findLargestObject) ? 4 : 0,
+                                         (findLargestObject ? CASCADE_FIND_BIGGEST_OBJECT : 0)
+                                            | CASCADE_SCALE_IMAGE,
+                                         minSize);
+        }
+
+        for (size_t i = 0; i < faces.size(); ++i)
+        {
+            rectangle(resized_cpu, faces[i], Scalar(255));
+        }
+
+        tm.stop();
+        double detectionTime = tm.getTimeMilli();
+        double fps = 1000 / detectionTime;
+
+        //print detections to console
+        cout << setfill(' ') << setprecision(2);
+        cout << setw(6) << fixed << fps << " FPS, " << faces.size() << " det";
+        if ((filterRects || findLargestObject) && !faces.empty())
+        {
+            for (size_t i = 0; i < faces.size(); ++i)
+            {
+                cout << ", [" << setw(4) << faces[i].x
+                     << ", " << setw(4) << faces[i].y
+                     << ", " << setw(4) << faces[i].width
+                     << ", " << setw(4) << faces[i].height << "]";
+            }
+        }
+        cout << endl;
+
+        cv::cvtColor(resized_cpu, frameDisp, COLOR_GRAY2BGR);
+        displayState(frameDisp, helpScreen, useGPU, findLargestObject, filterRects, fps);
+        imshow("result", frameDisp);
+
+        char key = (char)waitKey(5);
+        if (key == 27)
+        {
+            break;
+        }
+
+        switch (key)
+        {
+        case ' ':
+            useGPU = !useGPU;
+            break;
+        case 'm':
+        case 'M':
+            findLargestObject = !findLargestObject;
+            break;
+        case 'f':
+        case 'F':
+            filterRects = !filterRects;
+            break;
+        case '1':
+            scaleFactor *= 1.05;
+            break;
+        case 'q':
+        case 'Q':
+            scaleFactor /= 1.05;
+            break;
+        case 'h':
+        case 'H':
+            helpScreen = !helpScreen;
+            break;
+        }
+    }
+
+    return 0;
+}

modules/xobjdetect/samples/gpu/hog.cpp

@@ -0,0 +1,552 @@
+#include <iostream>
+#include <fstream>
+#include <string>
+#include <sstream>
+#include <iomanip>
+#include <stdexcept>
+#include <opencv2/core/utility.hpp>
+#include "opencv2/cudaobjdetect.hpp"
+#include "opencv2/highgui.hpp"
+#include "opencv2/xobjdetect.hpp"
+#include "opencv2/imgproc.hpp"
+
+using namespace std;
+using namespace cv;
+
+bool help_showed = false;
+
+class Args
+{
+public:
+    Args();
+    static Args read(int argc, char** argv);
+
+    string src;
+    bool src_is_folder;
+    bool src_is_video;
+    bool src_is_camera;
+    int camera_id;
+
+    bool svm_load;
+    string svm;
+
+    bool write_video;
+    string dst_video;
+    double dst_video_fps;
+
+    bool make_gray;
+
+    bool resize_src;
+    int width, height;
+
+    double scale;
+    int nlevels;
+    int gr_threshold;
+
+    double hit_threshold;
+    bool hit_threshold_auto;
+
+    int win_width;
+    int win_stride_width, win_stride_height;
+    int block_width;
+    int block_stride_width, block_stride_height;
+    int cell_width;
+    int nbins;
+
+    bool gamma_corr;
+};
+
+
+class App
+{
+public:
+    App(const Args& s);
+    void run();
+
+    void handleKey(char key);
+
+    void hogWorkBegin();
+    void hogWorkEnd();
+    string hogWorkFps() const;
+
+    void workBegin();
+    void workEnd();
+    string workFps() const;
+
+    string message() const;
+
+private:
+    App operator=(App&);
+
+    Args args;
+    bool running;
+
+    bool use_gpu;
+    bool make_gray;
+    double scale;
+    int gr_threshold;
+    int nlevels;
+    double hit_threshold;
+    bool gamma_corr;
+
+    int64 hog_work_begin;
+    double hog_work_fps;
+
+    int64 work_begin;
+    double work_fps;
+};
+
+static void printHelp()
+{
+    cout << "Histogram of Oriented Gradients descriptor and detector sample.\n"
+         << "\nUsage: hog\n"
+         << "  (<image>|--video <vide>|--camera <camera_id>) # frames source\n"
+         << "  or"
+         << "  (--folder <folder_path>) # load images from folder\n"
+         << "  [--svm <file> # load svm file"
+         << "  [--make_gray <true/false>] # convert image to gray one or not\n"
+         << "  [--resize_src <true/false>] # do resize of the source image or not\n"
+         << "  [--width <int>] # resized image width\n"
+         << "  [--height <int>] # resized image height\n"
+         << "  [--hit_threshold <double>] # classifying plane distance threshold (0.0 usually)\n"
+         << "  [--scale <double>] # HOG window scale factor\n"
+         << "  [--nlevels <int>] # max number of HOG window scales\n"
+         << "  [--win_width <int>] # width of the window\n"
+         << "  [--win_stride_width <int>] # distance by OX axis between neighbour wins\n"
+         << "  [--win_stride_height <int>] # distance by OY axis between neighbour wins\n"
+         << "  [--block_width <int>] # width of the block\n"
+         << "  [--block_stride_width <int>] # distance by 0X axis between neighbour blocks\n"
+         << "  [--block_stride_height <int>] # distance by 0Y axis between neighbour blocks\n"
+         << "  [--cell_width <int>] # width of the cell\n"
+         << "  [--nbins <int>] # number of bins\n"
+         << "  [--gr_threshold <int>] # merging similar rects constant\n"
+         << "  [--gamma_correct <int>] # do gamma correction or not\n"
+         << "  [--write_video <bool>] # write video or not\n"
+         << "  [--dst_video <path>] # output video path\n"
+         << "  [--dst_video_fps <double>] # output video fps\n";
+    help_showed = true;
+}
+
+int main(int argc, char** argv)
+{
+    try
+    {
+        Args args;
+        if (argc < 2)
+        {
+            printHelp();
+            args.camera_id = 0;
+            args.src_is_camera = true;
+        }
+        else
+        {
+            args = Args::read(argc, argv);
+            if (help_showed)
+                return -1;
+        }
+        App app(args);
+        app.run();
+    }
+    catch (const Exception& e) { return cout << "error: "  << e.what() << endl, 1; }
+    catch (const exception& e) { return cout << "error: "  << e.what() << endl, 1; }
+    catch(...) { return cout << "unknown exception" << endl, 1; }
+    return 0;
+}
+
+
+Args::Args()
+{
+    src_is_video = false;
+    src_is_camera = false;
+    src_is_folder = false;
+    svm_load = false;
+    camera_id = 0;
+
+    write_video = false;
+    dst_video_fps = 24.;
+
+    make_gray = false;
+
+    resize_src = false;
+    width = 640;
+    height = 480;
+
+    scale = 1.05;
+    nlevels = 13;
+    gr_threshold = 8;
+    hit_threshold = 1.4;
+    hit_threshold_auto = true;
+
+    win_width = 48;
+    win_stride_width = 8;
+    win_stride_height = 8;
+    block_width = 16;
+    block_stride_width = 8;
+    block_stride_height = 8;
+    cell_width = 8;
+    nbins = 9;
+
+    gamma_corr = true;
+}
+
+
+Args Args::read(int argc, char** argv)
+{
+    Args args;
+    for (int i = 1; i < argc; i++)
+    {
+        if (string(argv[i]) == "--make_gray") args.make_gray = (string(argv[++i]) == "true");
+        else if (string(argv[i]) == "--resize_src") args.resize_src = (string(argv[++i]) == "true");
+        else if (string(argv[i]) == "--width") args.width = atoi(argv[++i]);
+        else if (string(argv[i]) == "--height") args.height = atoi(argv[++i]);
+        else if (string(argv[i]) == "--hit_threshold")
+        {
+            args.hit_threshold = atof(argv[++i]);
+            args.hit_threshold_auto = false;
+        }
+        else if (string(argv[i]) == "--scale") args.scale = atof(argv[++i]);
+        else if (string(argv[i]) == "--nlevels") args.nlevels = atoi(argv[++i]);
+        else if (string(argv[i]) == "--win_width") args.win_width = atoi(argv[++i]);
+        else if (string(argv[i]) == "--win_stride_width") args.win_stride_width = atoi(argv[++i]);
+        else if (string(argv[i]) == "--win_stride_height") args.win_stride_height = atoi(argv[++i]);
+        else if (string(argv[i]) == "--block_width") args.block_width = atoi(argv[++i]);
+        else if (string(argv[i]) == "--block_stride_width") args.block_stride_width = atoi(argv[++i]);
+        else if (string(argv[i]) == "--block_stride_height") args.block_stride_height = atoi(argv[++i]);
+        else if (string(argv[i]) == "--cell_width") args.cell_width = atoi(argv[++i]);
+        else if (string(argv[i]) == "--nbins") args.nbins = atoi(argv[++i]);
+        else if (string(argv[i]) == "--gr_threshold") args.gr_threshold = atoi(argv[++i]);
+        else if (string(argv[i]) == "--gamma_correct") args.gamma_corr = (string(argv[++i]) == "true");
+        else if (string(argv[i]) == "--write_video") args.write_video = (string(argv[++i]) == "true");
+        else if (string(argv[i]) == "--dst_video") args.dst_video = argv[++i];
+        else if (string(argv[i]) == "--dst_video_fps") args.dst_video_fps = atof(argv[++i]);
+        else if (string(argv[i]) == "--help") printHelp();
+        else if (string(argv[i]) == "--video") { args.src = argv[++i]; args.src_is_video = true; }
+        else if (string(argv[i]) == "--camera") { args.camera_id = atoi(argv[++i]); args.src_is_camera = true; }
+        else if (string(argv[i]) == "--folder") { args.src = argv[++i]; args.src_is_folder = true;}
+        else if (string(argv[i]) == "--svm") { args.svm = argv[++i]; args.svm_load = true;}
+        else if (args.src.empty()) args.src = argv[i];
+        else throw runtime_error((string("unknown key: ") + argv[i]));
+    }
+    return args;
+}
+
+
+App::App(const Args& s)
+{
+    cv::cuda::printShortCudaDeviceInfo(cv::cuda::getDevice());
+
+    args = s;
+    cout << "\nControls:\n"
+         << "\tESC - exit\n"
+         << "\tm - change mode GPU <-> CPU\n"
+         << "\tg - convert image to gray or not\n"
+         << "\t1/q - increase/decrease HOG scale\n"
+         << "\t2/w - increase/decrease levels count\n"
+         << "\t3/e - increase/decrease HOG group threshold\n"
+         << "\t4/r - increase/decrease hit threshold\n"
+         << endl;
+
+    use_gpu = true;
+    make_gray = args.make_gray;
+    scale = args.scale;
+    gr_threshold = args.gr_threshold;
+    nlevels = args.nlevels;
+
+    if (args.hit_threshold_auto)
+        args.hit_threshold = args.win_width == 48 ? 1.4 : 0.;
+    hit_threshold = args.hit_threshold;
+
+    gamma_corr = args.gamma_corr;
+
+    cout << "Scale: " << scale << endl;
+    if (args.resize_src)
+        cout << "Resized source: (" << args.width << ", " << args.height << ")\n";
+    cout << "Group threshold: " << gr_threshold << endl;
+    cout << "Levels number: " << nlevels << endl;
+    cout << "Win size: (" << args.win_width << ", " << args.win_width*2 << ")\n";
+    cout << "Win stride: (" << args.win_stride_width << ", " << args.win_stride_height << ")\n";
+    cout << "Block size: (" << args.block_width << ", " << args.block_width << ")\n";
+    cout << "Block stride: (" << args.block_stride_width << ", " << args.block_stride_height << ")\n";
+    cout << "Cell size: (" << args.cell_width << ", " << args.cell_width << ")\n";
+    cout << "Bins number: " << args.nbins << endl;
+    cout << "Hit threshold: " << hit_threshold << endl;
+    cout << "Gamma correction: " << gamma_corr << endl;
+    cout << endl;
+}
+
+
+void App::run()
+{
+    running = true;
+    cv::VideoWriter video_writer;
+
+    Size win_stride(args.win_stride_width, args.win_stride_height);
+    Size win_size(args.win_width, args.win_width * 2);
+    Size block_size(args.block_width, args.block_width);
+    Size block_stride(args.block_stride_width, args.block_stride_height);
+    Size cell_size(args.cell_width, args.cell_width);
+
+    cv::Ptr<cv::cuda::HOG> gpu_hog = cv::cuda::HOG::create(win_size, block_size, block_stride, cell_size, args.nbins);
+    cv::HOGDescriptor cpu_hog(win_size, block_size, block_stride, cell_size, args.nbins);
+
+    if(args.svm_load) {
+        std::vector<float> svm_model;
+        const std::string model_file_name = args.svm;
+        FileStorage ifs(model_file_name, FileStorage::READ);
+        if (ifs.isOpened()) {
+            ifs["svm_detector"] >> svm_model;
+        } else {
+            const std::string what =
+                    "could not load model for hog classifier from file: "
+                    + model_file_name;
+            throw std::runtime_error(what);
+        }
+
+        // check if the variables are initialized
+        if (svm_model.empty()) {
+            const std::string what =
+                    "HoG classifier: svm model could not be loaded from file"
+                    + model_file_name;
+            throw std::runtime_error(what);
+        }
+
+        gpu_hog->setSVMDetector(svm_model);
+        cpu_hog.setSVMDetector(svm_model);
+    } else {
+        // Create HOG descriptors and detectors here
+        Mat detector = gpu_hog->getDefaultPeopleDetector();
+
+        gpu_hog->setSVMDetector(detector);
+        cpu_hog.setSVMDetector(detector);
+    }
+
+    cout << "gpusvmDescriptorSize : " << gpu_hog->getDescriptorSize()
+         << endl;
+    cout << "cpusvmDescriptorSize : " << cpu_hog.getDescriptorSize()
+         << endl;
+
+    while (running)
+    {
+        VideoCapture vc;
+        Mat frame;
+        vector<String> filenames;
+
+        unsigned int count = 1;
+
+        if (args.src_is_video)
+        {
+            vc.open(args.src.c_str());
+            if (!vc.isOpened())
+                throw runtime_error(string("can't open video file: " + args.src));
+            vc >> frame;
+        }
+        else if (args.src_is_folder) {
+            String folder = args.src;
+            cout << folder << endl;
+            glob(folder, filenames);
+            frame = imread(filenames[count]);	// 0 --> .gitignore
+            if (!frame.data)
+                cerr << "Problem loading image from folder!!!" << endl;
+        }
+        else if (args.src_is_camera)
+        {
+            vc.open(args.camera_id);
+            if (!vc.isOpened())
+            {
+                stringstream msg;
+                msg << "can't open camera: " << args.camera_id;
+                throw runtime_error(msg.str());
+            }
+            vc >> frame;
+        }
+        else
+        {
+            frame = imread(args.src);
+            if (frame.empty())
+                throw runtime_error(string("can't open image file: " + args.src));
+        }
+
+        Mat img_aux, img, img_to_show;
+        cuda::GpuMat gpu_img;
+
+        // Iterate over all frames
+        while (running && !frame.empty())
+        {
+            workBegin();
+
+            // Change format of the image
+            if (make_gray) cvtColor(frame, img_aux, COLOR_BGR2GRAY);
+            else if (use_gpu) cvtColor(frame, img_aux, COLOR_BGR2BGRA);
+            else frame.copyTo(img_aux);
+
+            // Resize image
+            if (args.resize_src) resize(img_aux, img, Size(args.width, args.height));
+            else img = img_aux;
+            img_to_show = img;
+
+            vector<Rect> found;
+
+            // Perform HOG classification
+            hogWorkBegin();
+            if (use_gpu)
+            {
+                gpu_img.upload(img);
+                gpu_hog->setNumLevels(nlevels);
+                gpu_hog->setHitThreshold(hit_threshold);
+                gpu_hog->setWinStride(win_stride);
+                gpu_hog->setScaleFactor(scale);
+                gpu_hog->setGroupThreshold(gr_threshold);
+                gpu_hog->detectMultiScale(gpu_img, found);
+            }
+            else
+            {
+                cpu_hog.nlevels = nlevels;
+                cpu_hog.detectMultiScale(img, found, hit_threshold, win_stride,
+                                         Size(0, 0), scale, gr_threshold);
+            }
+            hogWorkEnd();
+
+            // Draw positive classified windows
+            for (size_t i = 0; i < found.size(); i++)
+            {
+                Rect r = found[i];
+                rectangle(img_to_show, r.tl(), r.br(), Scalar(0, 255, 0), 3);
+            }
+
+            if (use_gpu)
+                putText(img_to_show, "Mode: GPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+            else
+                putText(img_to_show, "Mode: CPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+            putText(img_to_show, "FPS HOG: " + hogWorkFps(), Point(5, 65), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+            putText(img_to_show, "FPS total: " + workFps(), Point(5, 105), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+            imshow("opencv_gpu_hog", img_to_show);
+
+            if (args.src_is_video || args.src_is_camera) vc >> frame;
+            if (args.src_is_folder) {
+                count++;
+                if (count < filenames.size()) {
+                    frame = imread(filenames[count]);
+                } else {
+                    Mat empty;
+                    frame = empty;
+                }
+            }
+
+            workEnd();
+
+            if (args.write_video)
+            {
+                if (!video_writer.isOpened())
+                {
+                    video_writer.open(args.dst_video, VideoWriter::fourcc('x','v','i','d'), args.dst_video_fps,
+                                      img_to_show.size(), true);
+                    if (!video_writer.isOpened())
+                        throw std::runtime_error("can't create video writer");
+                }
+
+                if (make_gray) cvtColor(img_to_show, img, COLOR_GRAY2BGR);
+                else cvtColor(img_to_show, img, COLOR_BGRA2BGR);
+
+                video_writer << img;
+            }
+
+            handleKey((char)waitKey(3));
+        }
+    }
+}
+
+
+void App::handleKey(char key)
+{
+    switch (key)
+    {
+    case 27:
+        running = false;
+        break;
+    case 'm':
+    case 'M':
+        use_gpu = !use_gpu;
+        cout << "Switched to " << (use_gpu ? "CUDA" : "CPU") << " mode\n";
+        break;
+    case 'g':
+    case 'G':
+        make_gray = !make_gray;
+        cout << "Convert image to gray: " << (make_gray ? "YES" : "NO") << endl;
+        break;
+    case '1':
+        scale *= 1.05;
+        cout << "Scale: " << scale << endl;
+        break;
+    case 'q':
+    case 'Q':
+        scale /= 1.05;
+        cout << "Scale: " << scale << endl;
+        break;
+    case '2':
+        nlevels++;
+        cout << "Levels number: " << nlevels << endl;
+        break;
+    case 'w':
+    case 'W':
+        nlevels = max(nlevels - 1, 1);
+        cout << "Levels number: " << nlevels << endl;
+        break;
+    case '3':
+        gr_threshold++;
+        cout << "Group threshold: " << gr_threshold << endl;
+        break;
+    case 'e':
+    case 'E':
+        gr_threshold = max(0, gr_threshold - 1);
+        cout << "Group threshold: " << gr_threshold << endl;
+        break;
+    case '4':
+        hit_threshold+=0.25;
+        cout << "Hit threshold: " << hit_threshold << endl;
+        break;
+    case 'r':
+    case 'R':
+        hit_threshold = max(0.0, hit_threshold - 0.25);
+        cout << "Hit threshold: " << hit_threshold << endl;
+        break;
+    case 'c':
+    case 'C':
+        gamma_corr = !gamma_corr;
+        cout << "Gamma correction: " << gamma_corr << endl;
+        break;
+    }
+}
+
+
+inline void App::hogWorkBegin() { hog_work_begin = getTickCount(); }
+
+inline void App::hogWorkEnd()
+{
+    int64 delta = getTickCount() - hog_work_begin;
+    double freq = getTickFrequency();
+    hog_work_fps = freq / delta;
+}
+
+inline string App::hogWorkFps() const
+{
+    stringstream ss;
+    ss << hog_work_fps;
+    return ss.str();
+}
+
+
+inline void App::workBegin() { work_begin = getTickCount(); }
+
+inline void App::workEnd()
+{
+    int64 delta = getTickCount() - work_begin;
+    double freq = getTickFrequency();
+    work_fps = freq / delta;
+}
+
+inline string App::workFps() const
+{
+    stringstream ss;
+    ss << work_fps;
+    return ss.str();
+}

modules/xobjdetect/samples/hog_tapi.cpp

@@ -0,0 +1,352 @@
+#include <iostream>
+#include <fstream>
+#include <string>
+#include <sstream>
+#include <iomanip>
+#include <stdexcept>
+#include <opencv2/core/ocl.hpp>
+#include <opencv2/core/utility.hpp>
+#include "opencv2/imgcodecs.hpp"
+#include <opencv2/videoio.hpp>
+#include <opencv2/highgui.hpp>
+#include <opencv2/xobjdetect.hpp>
+#include <opencv2/imgproc.hpp>
+
+using namespace std;
+using namespace cv;
+
+class App
+{
+public:
+    App(CommandLineParser& cmd);
+    void run();
+    void handleKey(char key);
+    void hogWorkBegin();
+    void hogWorkEnd();
+    string hogWorkFps() const;
+    void workBegin();
+    void workEnd();
+    string workFps() const;
+private:
+    App operator=(App&);
+
+    //Args args;
+    bool running;
+    bool make_gray;
+    double scale;
+    double resize_scale;
+    int win_width;
+    int win_stride_width, win_stride_height;
+    int gr_threshold;
+    int nlevels;
+    double hit_threshold;
+    bool gamma_corr;
+
+    int64 hog_work_begin;
+    double hog_work_fps;
+    int64 work_begin;
+    double work_fps;
+
+    string img_source;
+    string vdo_source;
+    string output;
+    int camera_id;
+    bool write_once;
+};
+
+int main(int argc, char** argv)
+{
+    const char* keys =
+        "{ h help      |                | print help message }"
+        "{ i input     |                | specify input image}"
+        "{ c camera    | -1             | enable camera capturing }"
+        "{ v video     | vtest.avi | use video as input }"
+        "{ g gray      |                | convert image to gray one or not}"
+        "{ s scale     | 1.0            | resize the image before detect}"
+        "{ o output    |   output.avi   | specify output path when input is images}";
+    CommandLineParser cmd(argc, argv, keys);
+    if (cmd.has("help"))
+    {
+        cmd.printMessage();
+        return EXIT_SUCCESS;
+    }
+
+    App app(cmd);
+    try
+    {
+        app.run();
+    }
+    catch (const Exception& e)
+    {
+        return cout << "error: "  << e.what() << endl, 1;
+    }
+    catch (const exception& e)
+    {
+        return cout << "error: "  << e.what() << endl, 1;
+    }
+    catch(...)
+    {
+        return cout << "unknown exception" << endl, 1;
+    }
+    return EXIT_SUCCESS;
+}
+
+App::App(CommandLineParser& cmd)
+{
+    cout << "\nControls:\n"
+         << "\tESC - exit\n"
+         << "\tm - change mode GPU <-> CPU\n"
+         << "\tg - convert image to gray or not\n"
+         << "\to - save output image once, or switch on/off video save\n"
+         << "\t1/q - increase/decrease HOG scale\n"
+         << "\t2/w - increase/decrease levels count\n"
+         << "\t3/e - increase/decrease HOG group threshold\n"
+         << "\t4/r - increase/decrease hit threshold\n"
+         << endl;
+
+    make_gray = cmd.has("gray");
+    resize_scale = cmd.get<double>("s");
+    vdo_source = samples::findFileOrKeep(cmd.get<string>("v"));
+    img_source = cmd.get<string>("i");
+    output = cmd.get<string>("o");
+    camera_id = cmd.get<int>("c");
+
+    win_width = 48;
+    win_stride_width = 8;
+    win_stride_height = 8;
+    gr_threshold = 8;
+    nlevels = 13;
+    hit_threshold = 1.4;
+    scale = 1.05;
+    gamma_corr = true;
+    write_once = false;
+
+    cout << "Group threshold: " << gr_threshold << endl;
+    cout << "Levels number: " << nlevels << endl;
+    cout << "Win width: " << win_width << endl;
+    cout << "Win stride: (" << win_stride_width << ", " << win_stride_height << ")\n";
+    cout << "Hit threshold: " << hit_threshold << endl;
+    cout << "Gamma correction: " << gamma_corr << endl;
+    cout << endl;
+}
+
+void App::run()
+{
+    running = true;
+    VideoWriter video_writer;
+
+    Size win_size(win_width, win_width * 2);
+    Size win_stride(win_stride_width, win_stride_height);
+
+    // Create HOG descriptors and detectors here
+
+    HOGDescriptor hog(win_size, Size(16, 16), Size(8, 8), Size(8, 8), 9, 1, -1,
+                          HOGDescriptor::L2Hys, 0.2, gamma_corr, cv::HOGDescriptor::DEFAULT_NLEVELS);
+    hog.setSVMDetector( HOGDescriptor::getDaimlerPeopleDetector() );
+
+    while (running)
+    {
+        VideoCapture vc;
+        UMat frame;
+
+        if (vdo_source!="")
+        {
+            vc.open(vdo_source.c_str());
+            if (!vc.isOpened())
+                throw runtime_error(string("can't open video file: " + vdo_source));
+            vc >> frame;
+        }
+        else if (camera_id != -1)
+        {
+            vc.open(camera_id);
+            if (!vc.isOpened())
+            {
+                stringstream msg;
+                msg << "can't open camera: " << camera_id;
+                throw runtime_error(msg.str());
+            }
+            vc >> frame;
+        }
+        else
+        {
+            imread(img_source).copyTo(frame);
+            if (frame.empty())
+                throw runtime_error(string("can't open image file: " + img_source));
+        }
+
+        UMat img_aux, img, img_to_show;
+
+        // Iterate over all frames
+        while (running && !frame.empty())
+        {
+            workBegin();
+
+            // Change format of the image
+            if (make_gray) cvtColor(frame, img_aux, COLOR_BGR2GRAY );
+            else frame.copyTo(img_aux);
+
+            // Resize image
+            if (abs(scale-1.0)>0.001)
+            {
+                Size sz((int)((double)img_aux.cols/resize_scale), (int)((double)img_aux.rows/resize_scale));
+                resize(img_aux, img, sz, 0, 0, INTER_LINEAR_EXACT);
+            }
+            else img = img_aux;
+            img.copyTo(img_to_show);
+            hog.nlevels = nlevels;
+            vector<Rect> found;
+
+            // Perform HOG classification
+            hogWorkBegin();
+
+            hog.detectMultiScale(img, found, hit_threshold, win_stride,
+                    Size(0, 0), scale, gr_threshold);
+            hogWorkEnd();
+
+
+            // Draw positive classified windows
+            for (size_t i = 0; i < found.size(); i++)
+            {
+                rectangle(img_to_show, found[i], Scalar(0, 255, 0), 3);
+            }
+
+            putText(img_to_show, ocl::useOpenCL() ? "Mode: OpenCL"  : "Mode: CPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+            putText(img_to_show, "FPS (HOG only): " + hogWorkFps(), Point(5, 65), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+            putText(img_to_show, "FPS (total): " + workFps(), Point(5, 105), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+            imshow("opencv_hog", img_to_show);
+            if (vdo_source!="" || camera_id!=-1) vc >> frame;
+
+            workEnd();
+
+            if (output!="" && write_once)
+            {
+                if (img_source!="")     // write image
+                {
+                    write_once = false;
+                    imwrite(output, img_to_show);
+                }
+                else                    //write video
+                {
+                    if (!video_writer.isOpened())
+                    {
+                        video_writer.open(output, VideoWriter::fourcc('x','v','i','d'), 24,
+                                          img_to_show.size(), true);
+                        if (!video_writer.isOpened())
+                            throw std::runtime_error("can't create video writer");
+                    }
+
+                    if (make_gray) cvtColor(img_to_show, img, COLOR_GRAY2BGR);
+                    else cvtColor(img_to_show, img, COLOR_BGRA2BGR);
+
+                    video_writer << img;
+                }
+            }
+
+            handleKey((char)waitKey(3));
+        }
+    }
+}
+
+void App::handleKey(char key)
+{
+    switch (key)
+    {
+    case 27:
+        running = false;
+        break;
+    case 'm':
+    case 'M':
+        ocl::setUseOpenCL(!cv::ocl::useOpenCL());
+        cout << "Switched to " << (ocl::useOpenCL() ? "OpenCL enabled" : "CPU") << " mode\n";
+        break;
+    case 'g':
+    case 'G':
+        make_gray = !make_gray;
+        cout << "Convert image to gray: " << (make_gray ? "YES" : "NO") << endl;
+        break;
+    case '1':
+        scale *= 1.05;
+        cout << "Scale: " << scale << endl;
+        break;
+    case 'q':
+    case 'Q':
+        scale /= 1.05;
+        cout << "Scale: " << scale << endl;
+        break;
+    case '2':
+        nlevels++;
+        cout << "Levels number: " << nlevels << endl;
+        break;
+    case 'w':
+    case 'W':
+        nlevels = max(nlevels - 1, 1);
+        cout << "Levels number: " << nlevels << endl;
+        break;
+    case '3':
+        gr_threshold++;
+        cout << "Group threshold: " << gr_threshold << endl;
+        break;
+    case 'e':
+    case 'E':
+        gr_threshold = max(0, gr_threshold - 1);
+        cout << "Group threshold: " << gr_threshold << endl;
+        break;
+    case '4':
+        hit_threshold+=0.25;
+        cout << "Hit threshold: " << hit_threshold << endl;
+        break;
+    case 'r':
+    case 'R':
+        hit_threshold = max(0.0, hit_threshold - 0.25);
+        cout << "Hit threshold: " << hit_threshold << endl;
+        break;
+    case 'c':
+    case 'C':
+        gamma_corr = !gamma_corr;
+        cout << "Gamma correction: " << gamma_corr << endl;
+        break;
+    case 'o':
+    case 'O':
+        write_once = !write_once;
+        break;
+    }
+}
+
+
+inline void App::hogWorkBegin()
+{
+    hog_work_begin = getTickCount();
+}
+
+inline void App::hogWorkEnd()
+{
+    int64 delta = getTickCount() - hog_work_begin;
+    double freq = getTickFrequency();
+    hog_work_fps = freq / delta;
+}
+
+inline string App::hogWorkFps() const
+{
+    stringstream ss;
+    ss << hog_work_fps;
+    return ss.str();
+}
+
+inline void App::workBegin()
+{
+    work_begin = getTickCount();
+}
+
+inline void App::workEnd()
+{
+    int64 delta = getTickCount() - work_begin;
+    double freq = getTickFrequency();
+    work_fps = freq / delta;
+}
+
+inline string App::workFps() const
+{
+    stringstream ss;
+    ss << work_fps;
+    return ss.str();
+}

modules/xobjdetect/samples/java/tutorial_code/objectDetection/cascade_classifier/ObjectDetectionDemo.java

@@ -0,0 +1,98 @@
+import java.util.List;
+
+import org.opencv.core.Core;
+import org.opencv.core.Mat;
+import org.opencv.core.MatOfRect;
+import org.opencv.core.Point;
+import org.opencv.core.Rect;
+import org.opencv.core.Scalar;
+import org.opencv.core.Size;
+import org.opencv.highgui.HighGui;
+import org.opencv.imgproc.Imgproc;
+import org.opencv.xobjdetect.CascadeClassifier;
+import org.opencv.videoio.VideoCapture;
+
+class ObjectDetection {
+    public void detectAndDisplay(Mat frame, CascadeClassifier faceCascade, CascadeClassifier eyesCascade) {
+        Mat frameGray = new Mat();
+        Imgproc.cvtColor(frame, frameGray, Imgproc.COLOR_BGR2GRAY);
+        Imgproc.equalizeHist(frameGray, frameGray);
+
+        // -- Detect faces
+        MatOfRect faces = new MatOfRect();
+        faceCascade.detectMultiScale(frameGray, faces);
+
+        List<Rect> listOfFaces = faces.toList();
+        for (Rect face : listOfFaces) {
+            Point center = new Point(face.x + face.width / 2, face.y + face.height / 2);
+            Imgproc.ellipse(frame, center, new Size(face.width / 2, face.height / 2), 0, 0, 360,
+                    new Scalar(255, 0, 255));
+
+            Mat faceROI = frameGray.submat(face);
+
+            // -- In each face, detect eyes
+            MatOfRect eyes = new MatOfRect();
+            eyesCascade.detectMultiScale(faceROI, eyes);
+
+            List<Rect> listOfEyes = eyes.toList();
+            for (Rect eye : listOfEyes) {
+                Point eyeCenter = new Point(face.x + eye.x + eye.width / 2, face.y + eye.y + eye.height / 2);
+                int radius = (int) Math.round((eye.width + eye.height) * 0.25);
+                Imgproc.circle(frame, eyeCenter, radius, new Scalar(255, 0, 0), 4);
+            }
+        }
+
+        //-- Show what you got
+        HighGui.imshow("Capture - Face detection", frame );
+    }
+
+    public void run(String[] args) {
+        String filenameFaceCascade = args.length > 2 ? args[0] : "../../data/haarcascades/haarcascade_frontalface_alt.xml";
+        String filenameEyesCascade = args.length > 2 ? args[1] : "../../data/haarcascades/haarcascade_eye_tree_eyeglasses.xml";
+        int cameraDevice = args.length > 2 ? Integer.parseInt(args[2]) : 0;
+
+        CascadeClassifier faceCascade = new CascadeClassifier();
+        CascadeClassifier eyesCascade = new CascadeClassifier();
+
+        if (!faceCascade.load(filenameFaceCascade)) {
+            System.err.println("--(!)Error loading face cascade: " + filenameFaceCascade);
+            System.exit(0);
+        }
+        if (!eyesCascade.load(filenameEyesCascade)) {
+            System.err.println("--(!)Error loading eyes cascade: " + filenameEyesCascade);
+            System.exit(0);
+        }
+
+        VideoCapture capture = new VideoCapture(cameraDevice);
+        if (!capture.isOpened()) {
+            System.err.println("--(!)Error opening video capture");
+            System.exit(0);
+        }
+
+        Mat frame = new Mat();
+        while (capture.read(frame)) {
+            if (frame.empty()) {
+                System.err.println("--(!) No captured frame -- Break!");
+                break;
+            }
+
+            //-- 3. Apply the classifier to the frame
+            detectAndDisplay(frame, faceCascade, eyesCascade);
+
+            if (HighGui.waitKey(10) == 27) {
+                break;// escape
+            }
+        }
+
+        System.exit(0);
+    }
+}
+
+public class ObjectDetectionDemo {
+    public static void main(String[] args) {
+        // Load the native OpenCV library
+        System.loadLibrary(Core.NATIVE_LIBRARY_NAME);
+
+        new ObjectDetection().run(args);
+    }
+}

modules/xobjdetect/samples/objectDetection.cpp

@@ -0,0 +1,107 @@
+#include "opencv2/xobjdetect.hpp"
+#include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
+#include "opencv2/videoio.hpp"
+#include <iostream>
+
+using namespace std;
+using namespace cv;
+
+/** Function Headers */
+void detectAndDisplay( Mat frame );
+
+/** Global variables */
+CascadeClassifier face_cascade;
+CascadeClassifier eyes_cascade;
+
+/** @function main */
+int main( int argc, const char** argv )
+{
+    CommandLineParser parser(argc, argv,
+                             "{help h||}"
+                             "{face_cascade|data/haarcascades/haarcascade_frontalface_alt.xml|Path to face cascade.}"
+                             "{eyes_cascade|data/haarcascades/haarcascade_eye_tree_eyeglasses.xml|Path to eyes cascade.}"
+                             "{camera|0|Camera device number.}");
+
+    parser.about( "\nThis program demonstrates using the cv::CascadeClassifier class to detect objects (Face + eyes) in a video stream.\n"
+                  "You can use Haar or LBP features.\n\n" );
+    parser.printMessage();
+
+    String face_cascade_name = samples::findFile( parser.get<String>("face_cascade") );
+    String eyes_cascade_name = samples::findFile( parser.get<String>("eyes_cascade") );
+
+    //-- 1. Load the cascades
+    if( !face_cascade.load( face_cascade_name ) )
+    {
+        cout << "--(!)Error loading face cascade\n";
+        return -1;
+    };
+    if( !eyes_cascade.load( eyes_cascade_name ) )
+    {
+        cout << "--(!)Error loading eyes cascade\n";
+        return -1;
+    };
+
+    int camera_device = parser.get<int>("camera");
+    VideoCapture capture;
+    //-- 2. Read the video stream
+    capture.open( camera_device );
+    if ( ! capture.isOpened() )
+    {
+        cout << "--(!)Error opening video capture\n";
+        return -1;
+    }
+
+    Mat frame;
+    while ( capture.read(frame) )
+    {
+        if( frame.empty() )
+        {
+            cout << "--(!) No captured frame -- Break!\n";
+            break;
+        }
+
+        //-- 3. Apply the classifier to the frame
+        detectAndDisplay( frame );
+
+        if( waitKey(10) == 27 )
+        {
+            break; // escape
+        }
+    }
+    return 0;
+}
+
+/** @function detectAndDisplay */
+void detectAndDisplay( Mat frame )
+{
+    Mat frame_gray;
+    cvtColor( frame, frame_gray, COLOR_BGR2GRAY );
+    equalizeHist( frame_gray, frame_gray );
+
+    //-- Detect faces
+    std::vector<Rect> faces;
+    face_cascade.detectMultiScale( frame_gray, faces );
+
+    for ( size_t i = 0; i < faces.size(); i++ )
+    {
+        Point center( faces[i].x + faces[i].width/2, faces[i].y + faces[i].height/2 );
+        ellipse( frame, center, Size( faces[i].width/2, faces[i].height/2 ), 0, 0, 360, Scalar( 255, 0, 255 ), 4 );
+
+        Mat faceROI = frame_gray( faces[i] );
+
+        //-- In each face, detect eyes
+        std::vector<Rect> eyes;
+        eyes_cascade.detectMultiScale( faceROI, eyes );
+
+        for ( size_t j = 0; j < eyes.size(); j++ )
+        {
+            Point eye_center( faces[i].x + eyes[j].x + eyes[j].width/2, faces[i].y + eyes[j].y + eyes[j].height/2 );
+            int radius = cvRound( (eyes[j].width + eyes[j].height)*0.25 );
+            circle( frame, eye_center, radius, Scalar( 255, 0, 0 ), 4 );
+        }
+    }
+
+    //-- Show what you got
+    imshow( "Capture - Face detection", frame );
+}

modules/xobjdetect/samples/peopledetect.cpp

@@ -0,0 +1,129 @@
+// This file is part of OpenCV project.
+// It is subject to the license terms in the LICENSE file found in the top-level directory
+// of this distribution and at http://opencv.org/license.html
+
+#include <opencv2/xobjdetect.hpp>
+#include <opencv2/highgui.hpp>
+#include <opencv2/imgproc.hpp>
+#include <opencv2/videoio.hpp>
+#include <iostream>
+#include <iomanip>
+
+using namespace cv;
+using namespace std;
+
+class Detector
+{
+    enum Mode { Default, Daimler } m;
+    HOGDescriptor hog, hog_d;
+public:
+    Detector() : m(Default), hog(), hog_d(Size(48, 96), Size(16, 16), Size(8, 8), Size(8, 8), 9)
+    {
+        hog.setSVMDetector(HOGDescriptor::getDefaultPeopleDetector());
+        hog_d.setSVMDetector(HOGDescriptor::getDaimlerPeopleDetector());
+    }
+    void toggleMode() { m = (m == Default ? Daimler : Default); }
+    string modeName() const { return (m == Default ? "Default" : "Daimler"); }
+    vector<Rect> detect(InputArray img)
+    {
+        // Run the detector with default parameters. to get a higher hit-rate
+        // (and more false alarms, respectively), decrease the hitThreshold and
+        // groupThreshold (set groupThreshold to 0 to turn off the grouping completely).
+        vector<Rect> found;
+        if (m == Default)
+            hog.detectMultiScale(img, found, 0, Size(8,8), Size(), 1.05, 2, false);
+        else if (m == Daimler)
+            hog_d.detectMultiScale(img, found, 0, Size(8,8), Size(), 1.05, 2, true);
+        return found;
+    }
+    void adjustRect(Rect & r) const
+    {
+        // The HOG detector returns slightly larger rectangles than the real objects,
+        // so we slightly shrink the rectangles to get a nicer output.
+        r.x += cvRound(r.width*0.1);
+        r.width = cvRound(r.width*0.8);
+        r.y += cvRound(r.height*0.07);
+        r.height = cvRound(r.height*0.8);
+    }
+};
+
+static const string keys = "{ help h   |   | print help message }"
+                           "{ camera c | 0 | capture video from camera (device index starting from 0) }"
+                           "{ video v  |   | use video as input }";
+
+int main(int argc, char** argv)
+{
+    CommandLineParser parser(argc, argv, keys);
+    parser.about("This sample demonstrates the use of the HoG descriptor.");
+    if (parser.has("help"))
+    {
+        parser.printMessage();
+        return 0;
+    }
+    int camera = parser.get<int>("camera");
+    string file = parser.get<string>("video");
+    if (!parser.check())
+    {
+        parser.printErrors();
+        return 1;
+    }
+
+    VideoCapture cap;
+    if (file.empty())
+        cap.open(camera);
+    else
+    {
+        file = samples::findFileOrKeep(file);
+        cap.open(file);
+    }
+    if (!cap.isOpened())
+    {
+        cout << "Can not open video stream: '" << (file.empty() ? "<camera>" : file) << "'" << endl;
+        return 2;
+    }
+
+    cout << "Press 'q' or <ESC> to quit." << endl;
+    cout << "Press <space> to toggle between Default and Daimler detector" << endl;
+    Detector detector;
+    Mat frame;
+    for (;;)
+    {
+        cap >> frame;
+        if (frame.empty())
+        {
+            cout << "Finished reading: empty frame" << endl;
+            break;
+        }
+        int64 t = getTickCount();
+        vector<Rect> found = detector.detect(frame);
+        t = getTickCount() - t;
+
+        // show the window
+        {
+            ostringstream buf;
+            buf << "Mode: " << detector.modeName() << " ||| "
+                << "FPS: " << fixed << setprecision(1) << (getTickFrequency() / (double)t);
+            putText(frame, buf.str(), Point(10, 30), FONT_HERSHEY_PLAIN, 2.0, Scalar(0, 0, 255), 2, LINE_AA);
+        }
+        for (vector<Rect>::iterator i = found.begin(); i != found.end(); ++i)
+        {
+            Rect &r = *i;
+            detector.adjustRect(r);
+            rectangle(frame, r.tl(), r.br(), cv::Scalar(0, 255, 0), 2);
+        }
+        imshow("People detector", frame);
+
+        // interact with user
+        const char key = (char)waitKey(1);
+        if (key == 27 || key == 'q') // ESC
+        {
+            cout << "Exit requested" << endl;
+            break;
+        }
+        else if (key == ' ')
+        {
+            detector.toggleMode();
+        }
+    }
+    return 0;
+}

modules/xobjdetect/samples/python/common.py

@@ -0,0 +1,224 @@
+#!/usr/bin/env python
+
+'''
+This module contains some common routines used by other samples.
+'''
+
+from functools import reduce
+import numpy as np
+import cv2 as cv
+
+# built-in modules
+import os
+import itertools as it
+from contextlib import contextmanager
+
+image_extensions = ['.bmp', '.jpg', '.jpeg', '.png', '.tif', '.tiff', '.pbm', '.pgm', '.ppm']
+
+class Bunch(object):
+    def __init__(self, **kw):
+        self.__dict__.update(kw)
+    def __str__(self):
+        return str(self.__dict__)
+
+def splitfn(fn):
+    path, fn = os.path.split(fn)
+    name, ext = os.path.splitext(fn)
+    return path, name, ext
+
+def anorm2(a):
+    return (a*a).sum(-1)
+def anorm(a):
+    return np.sqrt( anorm2(a) )
+
+def homotrans(H, x, y):
+    xs = H[0, 0]*x + H[0, 1]*y + H[0, 2]
+    ys = H[1, 0]*x + H[1, 1]*y + H[1, 2]
+    s  = H[2, 0]*x + H[2, 1]*y + H[2, 2]
+    return xs/s, ys/s
+
+def to_rect(a):
+    a = np.ravel(a)
+    if len(a) == 2:
+        a = (0, 0, a[0], a[1])
+    return np.array(a, np.float64).reshape(2, 2)
+
+def rect2rect_mtx(src, dst):
+    src, dst = to_rect(src), to_rect(dst)
+    cx, cy = (dst[1] - dst[0]) / (src[1] - src[0])
+    tx, ty = dst[0] - src[0] * (cx, cy)
+    M = np.float64([[ cx,  0, tx],
+                    [  0, cy, ty],
+                    [  0,  0,  1]])
+    return M
+
+
+def lookat(eye, target, up = (0, 0, 1)):
+    fwd = np.asarray(target, np.float64) - eye
+    fwd /= anorm(fwd)
+    right = np.cross(fwd, up)
+    right /= anorm(right)
+    down = np.cross(fwd, right)
+    R = np.float64([right, down, fwd])
+    tvec = -np.dot(R, eye)
+    return R, tvec
+
+def mtx2rvec(R):
+    w, u, vt = cv.SVDecomp(R - np.eye(3))
+    p = vt[0] + u[:,0]*w[0]    # same as np.dot(R, vt[0])
+    c = np.dot(vt[0], p)
+    s = np.dot(vt[1], p)
+    axis = np.cross(vt[0], vt[1])
+    return axis * np.arctan2(s, c)
+
+def draw_str(dst, target, s):
+    x, y = target
+    cv.putText(dst, s, (x+1, y+1), cv.FONT_HERSHEY_PLAIN, 1.0, (0, 0, 0), thickness = 2, lineType=cv.LINE_AA)
+    cv.putText(dst, s, (x, y), cv.FONT_HERSHEY_PLAIN, 1.0, (255, 255, 255), lineType=cv.LINE_AA)
+
+class Sketcher:
+    def __init__(self, windowname, dests, colors_func):
+        self.prev_pt = None
+        self.windowname = windowname
+        self.dests = dests
+        self.colors_func = colors_func
+        self.dirty = False
+        self.show()
+        cv.setMouseCallback(self.windowname, self.on_mouse)
+
+    def show(self):
+        cv.imshow(self.windowname, self.dests[0])
+
+    def on_mouse(self, event, x, y, flags, param):
+        pt = (x, y)
+        if event == cv.EVENT_LBUTTONDOWN:
+            self.prev_pt = pt
+        elif event == cv.EVENT_LBUTTONUP:
+            self.prev_pt = None
+
+        if self.prev_pt and flags & cv.EVENT_FLAG_LBUTTON:
+            for dst, color in zip(self.dests, self.colors_func()):
+                cv.line(dst, self.prev_pt, pt, color, 5)
+            self.dirty = True
+            self.prev_pt = pt
+            self.show()
+
+
+# palette data from matplotlib/_cm.py
+_jet_data =   {'red':   ((0., 0, 0), (0.35, 0, 0), (0.66, 1, 1), (0.89,1, 1),
+                         (1, 0.5, 0.5)),
+               'green': ((0., 0, 0), (0.125,0, 0), (0.375,1, 1), (0.64,1, 1),
+                         (0.91,0,0), (1, 0, 0)),
+               'blue':  ((0., 0.5, 0.5), (0.11, 1, 1), (0.34, 1, 1), (0.65,0, 0),
+                         (1, 0, 0))}
+
+cmap_data = { 'jet' : _jet_data }
+
+def make_cmap(name, n=256):
+    data = cmap_data[name]
+    xs = np.linspace(0.0, 1.0, n)
+    channels = []
+    eps = 1e-6
+    for ch_name in ['blue', 'green', 'red']:
+        ch_data = data[ch_name]
+        xp, yp = [], []
+        for x, y1, y2 in ch_data:
+            xp += [x, x+eps]
+            yp += [y1, y2]
+        ch = np.interp(xs, xp, yp)
+        channels.append(ch)
+    return np.uint8(np.array(channels).T*255)
+
+def nothing(*arg, **kw):
+    pass
+
+def clock():
+    return cv.getTickCount() / cv.getTickFrequency()
+
+@contextmanager
+def Timer(msg):
+    print(msg, '...',)
+    start = clock()
+    try:
+        yield
+    finally:
+        print("%.2f ms" % ((clock()-start)*1000))
+
+class StatValue:
+    def __init__(self, smooth_coef = 0.5):
+        self.value = None
+        self.smooth_coef = smooth_coef
+    def update(self, v):
+        if self.value is None:
+            self.value = v
+        else:
+            c = self.smooth_coef
+            self.value = c * self.value + (1.0-c) * v
+
+class RectSelector:
+    def __init__(self, win, callback):
+        self.win = win
+        self.callback = callback
+        cv.setMouseCallback(win, self.onmouse)
+        self.drag_start = None
+        self.drag_rect = None
+    def onmouse(self, event, x, y, flags, param):
+        x, y = np.int16([x, y]) # BUG
+        if event == cv.EVENT_LBUTTONDOWN:
+            self.drag_start = (x, y)
+            return
+        if self.drag_start:
+            if flags & cv.EVENT_FLAG_LBUTTON:
+                xo, yo = self.drag_start
+                x0, y0 = np.minimum([xo, yo], [x, y])
+                x1, y1 = np.maximum([xo, yo], [x, y])
+                self.drag_rect = None
+                if x1-x0 > 0 and y1-y0 > 0:
+                    self.drag_rect = (x0, y0, x1, y1)
+            else:
+                rect = self.drag_rect
+                self.drag_start = None
+                self.drag_rect = None
+                if rect:
+                    self.callback(rect)
+    def draw(self, vis):
+        if not self.drag_rect:
+            return False
+        x0, y0, x1, y1 = self.drag_rect
+        cv.rectangle(vis, (x0, y0), (x1, y1), (0, 255, 0), 2)
+        return True
+    @property
+    def dragging(self):
+        return self.drag_rect is not None
+
+
+def grouper(n, iterable, fillvalue=None):
+    '''grouper(3, 'ABCDEFG', 'x') --> ABC DEF Gxx'''
+    args = [iter(iterable)] * n
+    output = it.zip_longest(fillvalue=fillvalue, *args)
+    return output
+
+def mosaic(w, imgs):
+    '''Make a grid from images.
+
+    w    -- number of grid columns
+    imgs -- images (must have same size and format)
+    '''
+    imgs = iter(imgs)
+    img0 = next(imgs)
+    pad = np.zeros_like(img0)
+    imgs = it.chain([img0], imgs)
+    rows = grouper(w, imgs, pad)
+    return np.vstack(list(map(np.hstack, rows)))
+
+def getsize(img):
+    h, w = img.shape[:2]
+    return w, h
+
+def mdot(*args):
+    return reduce(np.dot, args)
+
+def draw_keypoints(vis, keypoints, color = (0, 255, 255)):
+    for kp in keypoints:
+        x, y = kp.pt
+        cv.circle(vis, (int(x), int(y)), 2, color)

modules/xobjdetect/samples/python/facedetect.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python
+
+'''
+face detection using haar cascades
+
+USAGE:
+    facedetect.py [--cascade <cascade_fn>] [--nested-cascade <cascade_fn>] [<video_source>]
+'''
+
+# Python 2/3 compatibility
+from __future__ import print_function
+
+import numpy as np
+import cv2 as cv
+
+# local modules
+from video import create_capture
+from common import clock, draw_str
+
+
+def detect(img, cascade):
+    rects = cascade.detectMultiScale(img, scaleFactor=1.3, minNeighbors=4, minSize=(30, 30),
+                                     flags=cv.CASCADE_SCALE_IMAGE)
+    if len(rects) == 0:
+        return []
+    rects[:,2:] += rects[:,:2]
+    return rects
+
+def draw_rects(img, rects, color):
+    for x1, y1, x2, y2 in rects:
+        cv.rectangle(img, (x1, y1), (x2, y2), color, 2)
+
+def main():
+    import sys, getopt
+
+    args, video_src = getopt.getopt(sys.argv[1:], '', ['cascade=', 'nested-cascade='])
+    try:
+        video_src = video_src[0]
+    except:
+        video_src = 0
+    args = dict(args)
+    cascade_fn = args.get('--cascade', "haarcascades/haarcascade_frontalface_alt.xml")
+    nested_fn  = args.get('--nested-cascade', "haarcascades/haarcascade_eye.xml")
+
+    cascade = cv.CascadeClassifier(cv.samples.findFile(cascade_fn))
+    nested = cv.CascadeClassifier(cv.samples.findFile(nested_fn))
+
+    cam = create_capture(video_src, fallback='synth:bg={}:noise=0.05'.format(cv.samples.findFile('lena.jpg')))
+
+    while True:
+        _ret, img = cam.read()
+        gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
+        gray = cv.equalizeHist(gray)
+
+        t = clock()
+        rects = detect(gray, cascade)
+        vis = img.copy()
+        draw_rects(vis, rects, (0, 255, 0))
+        if not nested.empty():
+            for x1, y1, x2, y2 in rects:
+                roi = gray[y1:y2, x1:x2]
+                vis_roi = vis[y1:y2, x1:x2]
+                subrects = detect(roi.copy(), nested)
+                draw_rects(vis_roi, subrects, (255, 0, 0))
+        dt = clock() - t
+
+        draw_str(vis, (20, 20), 'time: %.1f ms' % (dt*1000))
+        cv.imshow('facedetect', vis)
+
+        if cv.waitKey(5) == 27:
+            break
+
+    print('Done')
+
+
+if __name__ == '__main__':
+    print(__doc__)
+    main()
+    cv.destroyAllWindows()

modules/xobjdetect/samples/python/peopledetect.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python
+
+'''
+example to detect upright people in images using HOG features
+
+Usage:
+    peopledetect.py <image_names>
+
+Press any key to continue, ESC to stop.
+'''
+
+# Python 2/3 compatibility
+from __future__ import print_function
+
+import numpy as np
+import cv2 as cv
+
+
+def inside(r, q):
+    rx, ry, rw, rh = r
+    qx, qy, qw, qh = q
+    return rx > qx and ry > qy and rx + rw < qx + qw and ry + rh < qy + qh
+
+
+def draw_detections(img, rects, thickness = 1):
+    for x, y, w, h in rects:
+        # the HOG detector returns slightly larger rectangles than the real objects.
+        # so we slightly shrink the rectangles to get a nicer output.
+        pad_w, pad_h = int(0.15*w), int(0.05*h)
+        cv.rectangle(img, (x+pad_w, y+pad_h), (x+w-pad_w, y+h-pad_h), (0, 255, 0), thickness)
+
+
+def main():
+    import sys
+    from glob import glob
+    import itertools as it
+
+    hog = cv.HOGDescriptor()
+    hog.setSVMDetector( cv.HOGDescriptor_getDefaultPeopleDetector() )
+
+    default = [cv.samples.findFile('basketball2.png')] if len(sys.argv[1:]) == 0 else []
+
+    for fn in it.chain(*map(glob, default + sys.argv[1:])):
+        print(fn, ' - ',)
+        try:
+            img = cv.imread(fn)
+            if img is None:
+                print('Failed to load image file:', fn)
+                continue
+        except:
+            print('loading error')
+            continue
+
+        found, _w = hog.detectMultiScale(img, winStride=(8,8), padding=(32,32), scale=1.05)
+        found_filtered = []
+        for ri, r in enumerate(found):
+            for qi, q in enumerate(found):
+                if ri != qi and inside(r, q):
+                    break
+            else:
+                found_filtered.append(r)
+        draw_detections(img, found)
+        draw_detections(img, found_filtered, 3)
+        print('%d (%d) found' % (len(found_filtered), len(found)))
+        cv.imshow('img', img)
+        ch = cv.waitKey()
+        if ch == 27:
+            break
+
+    print('Done')
+
+
+if __name__ == '__main__':
+    print(__doc__)
+    main()
+    cv.destroyAllWindows()

modules/xobjdetect/samples/python/tst_scene_render.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python
+
+
+# Python 2/3 compatibility
+from __future__ import print_function
+
+import numpy as np
+import cv2 as cv
+
+from numpy import pi, sin, cos
+
+
+defaultSize = 512
+
+class TestSceneRender():
+
+    def __init__(self, bgImg = None, fgImg = None,
+        deformation = False, speed = 0.25, **params):
+        self.time = 0.0
+        self.timeStep = 1.0 / 30.0
+        self.foreground = fgImg
+        self.deformation = deformation
+        self.speed = speed
+
+        if bgImg is not None:
+            self.sceneBg = bgImg.copy()
+        else:
+            self.sceneBg = np.zeros((defaultSize, defaultSize,3), np.uint8)
+
+        self.w = self.sceneBg.shape[0]
+        self.h = self.sceneBg.shape[1]
+
+        if fgImg is not None:
+            self.foreground = fgImg.copy()
+            self.center = self.currentCenter = (int(self.w/2 - fgImg.shape[0]/2), int(self.h/2 - fgImg.shape[1]/2))
+
+            self.xAmpl = self.sceneBg.shape[0] - (self.center[0] + fgImg.shape[0])
+            self.yAmpl = self.sceneBg.shape[1] - (self.center[1] + fgImg.shape[1])
+
+        self.initialRect = np.array([ (self.h/2, self.w/2), (self.h/2, self.w/2 + self.w/10),
+         (self.h/2 + self.h/10, self.w/2 + self.w/10), (self.h/2 + self.h/10, self.w/2)]).astype(int)
+        self.currentRect = self.initialRect
+
+    def getXOffset(self, time):
+        return int( self.xAmpl*cos(time*self.speed))
+
+
+    def getYOffset(self, time):
+        return int(self.yAmpl*sin(time*self.speed))
+
+    def setInitialRect(self, rect):
+        self.initialRect = rect
+
+    def getRectInTime(self, time):
+
+        if self.foreground is not None:
+            tmp = np.array(self.center) + np.array((self.getXOffset(time), self.getYOffset(time)))
+            x0, y0 = tmp
+            x1, y1 = tmp + self.foreground.shape[0:2]
+            return np.array([y0, x0, y1, x1])
+        else:
+            x0, y0 = self.initialRect[0] + np.array((self.getXOffset(time), self.getYOffset(time)))
+            x1, y1 = self.initialRect[2] + np.array((self.getXOffset(time), self.getYOffset(time)))
+            return np.array([y0, x0, y1, x1])
+
+    def getCurrentRect(self):
+
+        if self.foreground is not None:
+
+            x0 = self.currentCenter[0]
+            y0 = self.currentCenter[1]
+            x1 = self.currentCenter[0] + self.foreground.shape[0]
+            y1 = self.currentCenter[1] + self.foreground.shape[1]
+            return np.array([y0, x0, y1, x1])
+        else:
+            x0, y0 = self.currentRect[0]
+            x1, y1 = self.currentRect[2]
+            return np.array([x0, y0, x1, y1])
+
+    def getNextFrame(self):
+        img = self.sceneBg.copy()
+
+        if self.foreground is not None:
+            self.currentCenter = (self.center[0] + self.getXOffset(self.time), self.center[1] + self.getYOffset(self.time))
+            img[self.currentCenter[0]:self.currentCenter[0]+self.foreground.shape[0],
+             self.currentCenter[1]:self.currentCenter[1]+self.foreground.shape[1]] = self.foreground
+        else:
+            self.currentRect = self.initialRect + int( 30*cos(self.time*self.speed) + 50*sin(self.time*self.speed))
+            if self.deformation:
+                self.currentRect[1:3] += int(self.h/20*cos(self.time))
+            cv.fillConvexPoly(img, self.currentRect, (0, 0, 255))
+
+        self.time += self.timeStep
+        return img
+
+    def resetTime(self):
+        self.time = 0.0
+
+
+def main():
+    backGr = cv.imread(cv.samples.findFile('graf1.png'))
+    fgr = cv.imread(cv.samples.findFile('box.png'))
+
+    render = TestSceneRender(backGr, fgr)
+
+    while True:
+
+        img = render.getNextFrame()
+        cv.imshow('img', img)
+
+        ch = cv.waitKey(3)
+        if  ch == 27:
+            break
+
+    print('Done')
+
+
+if __name__ == '__main__':
+    print(__doc__)
+    main()
+    cv.destroyAllWindows()

modules/xobjdetect/samples/python/tutorial_code/objectDetection/cascade_classifier/objectDetection.py

@@ -0,0 +1,61 @@
+from __future__ import print_function
+import cv2 as cv
+import argparse
+
+def detectAndDisplay(frame):
+    frame_gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
+    frame_gray = cv.equalizeHist(frame_gray)
+
+    #-- Detect faces
+    faces = face_cascade.detectMultiScale(frame_gray)
+    for (x,y,w,h) in faces:
+        center = (x + w//2, y + h//2)
+        frame = cv.ellipse(frame, center, (w//2, h//2), 0, 0, 360, (255, 0, 255), 4)
+
+        faceROI = frame_gray[y:y+h,x:x+w]
+        #-- In each face, detect eyes
+        eyes = eyes_cascade.detectMultiScale(faceROI)
+        for (x2,y2,w2,h2) in eyes:
+            eye_center = (x + x2 + w2//2, y + y2 + h2//2)
+            radius = int(round((w2 + h2)*0.25))
+            frame = cv.circle(frame, eye_center, radius, (255, 0, 0 ), 4)
+
+    cv.imshow('Capture - Face detection', frame)
+
+parser = argparse.ArgumentParser(description='Code for Cascade Classifier tutorial.')
+parser.add_argument('--face_cascade', help='Path to face cascade.', default='data/haarcascades/haarcascade_frontalface_alt.xml')
+parser.add_argument('--eyes_cascade', help='Path to eyes cascade.', default='data/haarcascades/haarcascade_eye_tree_eyeglasses.xml')
+parser.add_argument('--camera', help='Camera divide number.', type=int, default=0)
+args = parser.parse_args()
+
+face_cascade_name = args.face_cascade
+eyes_cascade_name = args.eyes_cascade
+
+face_cascade = cv.CascadeClassifier()
+eyes_cascade = cv.CascadeClassifier()
+
+#-- 1. Load the cascades
+if not face_cascade.load(cv.samples.findFile(face_cascade_name)):
+    print('--(!)Error loading face cascade')
+    exit(0)
+if not eyes_cascade.load(cv.samples.findFile(eyes_cascade_name)):
+    print('--(!)Error loading eyes cascade')
+    exit(0)
+
+camera_device = args.camera
+#-- 2. Read the video stream
+cap = cv.VideoCapture(camera_device)
+if not cap.isOpened:
+    print('--(!)Error opening video capture')
+    exit(0)
+
+while True:
+    ret, frame = cap.read()
+    if frame is None:
+        print('--(!) No captured frame -- Break!')
+        break
+
+    detectAndDisplay(frame)
+
+    if cv.waitKey(10) == 27:
+        break

modules/xobjdetect/samples/python/video.py

@@ -0,0 +1,228 @@
+#!/usr/bin/env python
+
+'''
+Video capture sample.
+
+Sample shows how VideoCapture class can be used to acquire video
+frames from a camera of a movie file. Also the sample provides
+an example of procedural video generation by an object, mimicking
+the VideoCapture interface (see Chess class).
+
+'create_capture' is a convenience function for capture creation,
+falling back to procedural video in case of error.
+
+Usage:
+    video.py [--shotdir <shot path>] [source0] [source1] ...'
+
+    sourceN is an
+     - integer number for camera capture
+     - name of video file
+     - synth:<params> for procedural video
+
+Synth examples:
+    synth:bg=lena.jpg:noise=0.1
+    synth:class=chess:bg=lena.jpg:noise=0.1:size=640x480
+
+Keys:
+    ESC    - exit
+    SPACE  - save current frame to <shot path> directory
+
+'''
+
+# Python 2/3 compatibility
+from __future__ import print_function
+
+import numpy as np
+import cv2 as cv
+
+import re
+
+from numpy import pi, sin, cos
+
+# local modules
+from tst_scene_render import TestSceneRender
+import common
+
+class VideoSynthBase(object):
+    def __init__(self, size=None, noise=0.0, bg = None, **params):
+        self.bg = None
+        self.frame_size = (640, 480)
+        if bg is not None:
+            self.bg = cv.imread(cv.samples.findFile(bg))
+            h, w = self.bg.shape[:2]
+            self.frame_size = (w, h)
+
+        if size is not None:
+            w, h = map(int, size.split('x'))
+            self.frame_size = (w, h)
+            self.bg = cv.resize(self.bg, self.frame_size)
+
+        self.noise = float(noise)
+
+    def render(self, dst):
+        pass
+
+    def read(self, dst=None):
+        w, h = self.frame_size
+
+        if self.bg is None:
+            buf = np.zeros((h, w, 3), np.uint8)
+        else:
+            buf = self.bg.copy()
+
+        self.render(buf)
+
+        if self.noise > 0.0:
+            noise = np.zeros((h, w, 3), np.int8)
+            cv.randn(noise, np.zeros(3), np.ones(3)*255*self.noise)
+            buf = cv.add(buf, noise, dtype=cv.CV_8UC3)
+        return True, buf
+
+    def isOpened(self):
+        return True
+
+class Book(VideoSynthBase):
+    def __init__(self, **kw):
+        super(Book, self).__init__(**kw)
+        backGr = cv.imread(cv.samples.findFile('graf1.png'))
+        fgr = cv.imread(cv.samples.findFile('box.png'))
+        self.render = TestSceneRender(backGr, fgr, speed = 1)
+
+    def read(self, dst=None):
+        noise = np.zeros(self.render.sceneBg.shape, np.int8)
+        cv.randn(noise, np.zeros(3), np.ones(3)*255*self.noise)
+
+        return True, cv.add(self.render.getNextFrame(), noise, dtype=cv.CV_8UC3)
+
+class Cube(VideoSynthBase):
+    def __init__(self, **kw):
+        super(Cube, self).__init__(**kw)
+        self.render = TestSceneRender(cv.imread(cv.samples.findFile('pca_test1.jpg')), deformation = True,  speed = 1)
+
+    def read(self, dst=None):
+        noise = np.zeros(self.render.sceneBg.shape, np.int8)
+        cv.randn(noise, np.zeros(3), np.ones(3)*255*self.noise)
+
+        return True, cv.add(self.render.getNextFrame(), noise, dtype=cv.CV_8UC3)
+
+class Chess(VideoSynthBase):
+    def __init__(self, **kw):
+        super(Chess, self).__init__(**kw)
+
+        w, h = self.frame_size
+
+        self.grid_size = sx, sy = 10, 7
+        white_quads = []
+        black_quads = []
+        for i, j in np.ndindex(sy, sx):
+            q = [[j, i, 0], [j+1, i, 0], [j+1, i+1, 0], [j, i+1, 0]]
+            [white_quads, black_quads][(i + j) % 2].append(q)
+        self.white_quads = np.float32(white_quads)
+        self.black_quads = np.float32(black_quads)
+
+        fx = 0.9
+        self.K = np.float64([[fx*w, 0, 0.5*(w-1)],
+                        [0, fx*w, 0.5*(h-1)],
+                        [0.0,0.0,      1.0]])
+
+        self.dist_coef = np.float64([-0.2, 0.1, 0, 0])
+        self.t = 0
+
+    def draw_quads(self, img, quads, color = (0, 255, 0)):
+        img_quads = cv.projectPoints(quads.reshape(-1, 3), self.rvec, self.tvec, self.K, self.dist_coef) [0]
+        img_quads.shape = quads.shape[:2] + (2,)
+        for q in img_quads:
+            cv.fillConvexPoly(img, np.int32(q*4), color, cv.LINE_AA, shift=2)
+
+    def render(self, dst):
+        t = self.t
+        self.t += 1.0/30.0
+
+        sx, sy = self.grid_size
+        center = np.array([0.5*sx, 0.5*sy, 0.0])
+        phi = pi/3 + sin(t*3)*pi/8
+        c, s = cos(phi), sin(phi)
+        ofs = np.array([sin(1.2*t), cos(1.8*t), 0]) * sx * 0.2
+        eye_pos = center + np.array([cos(t)*c, sin(t)*c, s]) * 15.0 + ofs
+        target_pos = center + ofs
+
+        R, self.tvec = common.lookat(eye_pos, target_pos)
+        self.rvec = common.mtx2rvec(R)
+
+        self.draw_quads(dst, self.white_quads, (245, 245, 245))
+        self.draw_quads(dst, self.black_quads, (10, 10, 10))
+
+
+classes = dict(chess=Chess, book=Book, cube=Cube)
+
+presets = dict(
+    empty = 'synth:',
+    lena = 'synth:bg=lena.jpg:noise=0.1',
+    chess = 'synth:class=chess:bg=lena.jpg:noise=0.1:size=640x480',
+    book = 'synth:class=book:bg=graf1.png:noise=0.1:size=640x480',
+    cube = 'synth:class=cube:bg=pca_test1.jpg:noise=0.0:size=640x480'
+)
+
+
+def create_capture(source = 0, fallback = presets['chess']):
+    '''source: <int> or '<int>|<filename>|synth [:<param_name>=<value> [:...]]'
+    '''
+    source = str(source).strip()
+
+    # Win32: handle drive letter ('c:', ...)
+    source = re.sub(r'(^|=)([a-zA-Z]):([/\\a-zA-Z0-9])', r'\1?disk\2?\3', source)
+    chunks = source.split(':')
+    chunks = [re.sub(r'\?disk([a-zA-Z])\?', r'\1:', s) for s in chunks]
+
+    source = chunks[0]
+    try: source = int(source)
+    except ValueError: pass
+    params = dict( s.split('=') for s in chunks[1:] )
+
+    cap = None
+    if source == 'synth':
+        Class = classes.get(params.get('class', None), VideoSynthBase)
+        try: cap = Class(**params)
+        except: pass
+    else:
+        cap = cv.VideoCapture(source)
+        if 'size' in params:
+            w, h = map(int, params['size'].split('x'))
+            cap.set(cv.CAP_PROP_FRAME_WIDTH, w)
+            cap.set(cv.CAP_PROP_FRAME_HEIGHT, h)
+    if cap is None or not cap.isOpened():
+        print('Warning: unable to open video source: ', source)
+        if fallback is not None:
+            return create_capture(fallback, None)
+    return cap
+
+if __name__ == '__main__':
+    import sys
+    import getopt
+
+    print(__doc__)
+
+    args, sources = getopt.getopt(sys.argv[1:], '', 'shotdir=')
+    args = dict(args)
+    shotdir = args.get('--shotdir', '.')
+    if len(sources) == 0:
+        sources = [ 0 ]
+
+    caps = list(map(create_capture, sources))
+    shot_idx = 0
+    while True:
+        imgs = []
+        for i, cap in enumerate(caps):
+            ret, img = cap.read()
+            imgs.append(img)
+            cv.imshow('capture %d' % i, img)
+        ch = cv.waitKey(1)
+        if ch == 27:
+            break
+        if ch == ord(' '):
+            for i, img in enumerate(imgs):
+                fn = '%s/shot_%d_%03d.bmp' % (shotdir, i, shot_idx)
+                cv.imwrite(fn, img)
+                print(fn, 'saved')
+            shot_idx += 1
+    cv.destroyAllWindows()

modules/xobjdetect/samples/smiledetect.cpp

@@ -0,0 +1,215 @@
+#include "opencv2/xobjdetect.hpp"
+#include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
+#include "opencv2/videoio.hpp"
+#include <iostream>
+
+using namespace std;
+using namespace cv;
+
+static void help(const char** argv)
+{
+    cout << "\nThis program demonstrates the smile detector.\n"
+            "Usage:\n" <<
+            argv[0] << " [--cascade=<cascade_path> this is the frontal face classifier]\n"
+            "   [--smile-cascade=[<smile_cascade_path>]]\n"
+            "   [--scale=<image scale greater or equal to 1, try 2.0 for example. The larger the faster the processing>]\n"
+            "   [--try-flip]\n"
+            "   [video_filename|camera_index]\n\n"
+            "Example:\n" <<
+            argv[0] << " --cascade=\"data/haarcascades/haarcascade_frontalface_alt.xml\" --smile-cascade=\"data/haarcascades/haarcascade_smile.xml\" --scale=2.0\n\n"
+            "During execution:\n\tHit any key to quit.\n"
+            "\tUsing OpenCV version " << CV_VERSION << "\n" << endl;
+}
+
+void detectAndDraw( Mat& img, CascadeClassifier& cascade,
+                    CascadeClassifier& nestedCascade,
+                    double scale, bool tryflip );
+
+string cascadeName;
+string nestedCascadeName;
+
+int main( int argc, const char** argv )
+{
+    VideoCapture capture;
+    Mat frame, image;
+    string inputName;
+    bool tryflip;
+
+    help(argv);
+
+    CascadeClassifier cascade, nestedCascade;
+    double scale;
+    cv::CommandLineParser parser(argc, argv,
+        "{help h||}{scale|1|}"
+        "{cascade|data/haarcascades/haarcascade_frontalface_alt.xml|}"
+        "{smile-cascade|data/haarcascades/haarcascade_smile.xml|}"
+        "{try-flip||}{@input||}");
+    if (parser.has("help"))
+    {
+        help(argv);
+        return 0;
+    }
+    cascadeName = samples::findFile(parser.get<string>("cascade"));
+    nestedCascadeName = samples::findFile(parser.get<string>("smile-cascade"));
+    tryflip = parser.has("try-flip");
+    inputName = parser.get<string>("@input");
+    scale = parser.get<int>("scale");
+    if (!parser.check())
+    {
+        help(argv);
+        return 1;
+    }
+    if (scale < 1)
+        scale = 1;
+    if( !cascade.load( cascadeName ) )
+    {
+        cerr << "ERROR: Could not load face cascade" << endl;
+        help(argv);
+        return -1;
+    }
+    if( !nestedCascade.load( nestedCascadeName ) )
+    {
+        cerr << "ERROR: Could not load smile cascade" << endl;
+        help(argv);
+        return -1;
+    }
+    if( inputName.empty() || (isdigit(inputName[0]) && inputName.size() == 1) )
+    {
+        int c = inputName.empty() ? 0 : inputName[0] - '0' ;
+        if(!capture.open(c))
+            cout << "Capture from camera #" <<  c << " didn't work" << endl;
+    }
+    else if( inputName.size() )
+    {
+        inputName = samples::findFileOrKeep(inputName);
+        if(!capture.open( inputName ))
+            cout << "Could not read " << inputName << endl;
+    }
+
+    if( capture.isOpened() )
+    {
+        cout << "Video capturing has been started ..." << endl;
+        cout << endl << "NOTE: Smile intensity will only be valid after a first smile has been detected" << endl;
+
+        for(;;)
+        {
+            capture >> frame;
+            if( frame.empty() )
+                break;
+
+            Mat frame1 = frame.clone();
+            detectAndDraw( frame1, cascade, nestedCascade, scale, tryflip );
+
+            char c = (char)waitKey(10);
+            if( c == 27 || c == 'q' || c == 'Q' )
+                break;
+        }
+    }
+    else
+    {
+        cerr << "ERROR: Could not initiate capture" << endl;
+        help(argv);
+        return -1;
+    }
+
+    return 0;
+}
+
+void detectAndDraw( Mat& img, CascadeClassifier& cascade,
+                    CascadeClassifier& nestedCascade,
+                    double scale, bool tryflip)
+{
+    vector<Rect> faces, faces2;
+    const static Scalar colors[] =
+    {
+        Scalar(255,0,0),
+        Scalar(255,128,0),
+        Scalar(255,255,0),
+        Scalar(0,255,0),
+        Scalar(0,128,255),
+        Scalar(0,255,255),
+        Scalar(0,0,255),
+        Scalar(255,0,255)
+    };
+    Mat gray, smallImg;
+
+    cvtColor( img, gray, COLOR_BGR2GRAY );
+
+    double fx = 1 / scale;
+    resize( gray, smallImg, Size(), fx, fx, INTER_LINEAR_EXACT );
+    equalizeHist( smallImg, smallImg );
+
+    cascade.detectMultiScale( smallImg, faces,
+        1.1, 2, 0
+        //|CASCADE_FIND_BIGGEST_OBJECT
+        //|CASCADE_DO_ROUGH_SEARCH
+        |CASCADE_SCALE_IMAGE,
+        Size(30, 30) );
+    if( tryflip )
+    {
+        flip(smallImg, smallImg, 1);
+        cascade.detectMultiScale( smallImg, faces2,
+                                 1.1, 2, 0
+                                 //|CASCADE_FIND_BIGGEST_OBJECT
+                                 //|CASCADE_DO_ROUGH_SEARCH
+                                 |CASCADE_SCALE_IMAGE,
+                                 Size(30, 30) );
+        for( vector<Rect>::const_iterator r = faces2.begin(); r != faces2.end(); ++r )
+        {
+            faces.push_back(Rect(smallImg.cols - r->x - r->width, r->y, r->width, r->height));
+        }
+    }
+
+    for ( size_t i = 0; i < faces.size(); i++ )
+    {
+        Rect r = faces[i];
+        Mat smallImgROI;
+        vector<Rect> nestedObjects;
+        Point center;
+        Scalar color = colors[i%8];
+        int radius;
+
+        double aspect_ratio = (double)r.width/r.height;
+        if( 0.75 < aspect_ratio && aspect_ratio < 1.3 )
+        {
+            center.x = cvRound((r.x + r.width*0.5)*scale);
+            center.y = cvRound((r.y + r.height*0.5)*scale);
+            radius = cvRound((r.width + r.height)*0.25*scale);
+            circle( img, center, radius, color, 3, 8, 0 );
+        }
+        else
+            rectangle( img, Point(cvRound(r.x*scale), cvRound(r.y*scale)),
+                       Point(cvRound((r.x + r.width-1)*scale), cvRound((r.y + r.height-1)*scale)),
+                       color, 3, 8, 0);
+
+        const int half_height=cvRound((float)r.height/2);
+        r.y=r.y + half_height;
+        r.height = half_height-1;
+        smallImgROI = smallImg( r );
+        nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
+            1.1, 0, 0
+            //|CASCADE_FIND_BIGGEST_OBJECT
+            //|CASCADE_DO_ROUGH_SEARCH
+            //|CASCADE_DO_CANNY_PRUNING
+            |CASCADE_SCALE_IMAGE,
+            Size(30, 30) );
+
+        // The number of detected neighbors depends on image size (and also illumination, etc.). The
+        // following steps use a floating minimum and maximum of neighbors. Intensity thus estimated will be
+        //accurate only after a first smile has been displayed by the user.
+        const int smile_neighbors = (int)nestedObjects.size();
+        static int max_neighbors=-1;
+        static int min_neighbors=-1;
+        if (min_neighbors == -1) min_neighbors = smile_neighbors;
+        max_neighbors = MAX(max_neighbors, smile_neighbors);
+
+        // Draw rectangle on the left side of the image reflecting smile intensity
+        float intensityZeroOne = ((float)smile_neighbors - min_neighbors) / (max_neighbors - min_neighbors + 1);
+        int rect_height = cvRound((float)img.rows * intensityZeroOne);
+        Scalar col = Scalar((float)255 * intensityZeroOne, 0, 0);
+        rectangle(img, Point(0, img.rows), Point(img.cols/10, img.rows - rect_height), col, -1);
+    }
+
+    imshow( "result", img );
+}

modules/xobjdetect/samples/ufacedetect.cpp

@@ -0,0 +1,253 @@
+#include "opencv2/xobjdetect.hpp"
+#include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
+#include "opencv2/core/ocl.hpp"
+#include <iostream>
+
+using namespace std;
+using namespace cv;
+
+static void help()
+{
+    cout << "\nThis program demonstrates the cascade recognizer. Now you can use Haar or LBP features.\n"
+            "This classifier can recognize many kinds of rigid objects, once the appropriate classifier is trained.\n"
+            "It's most known use is for faces.\n"
+            "Usage:\n"
+            "./ufacedetect [--cascade=<cascade_path> this is the primary trained classifier such as frontal face]\n"
+               "   [--nested-cascade[=nested_cascade_path this an optional secondary classifier such as eyes]]\n"
+               "   [--scale=<image scale greater or equal to 1, try 1.3 for example>]\n"
+               "   [--try-flip]\n"
+               "   [filename|camera_index]\n\n"
+            "see facedetect.cmd for one call:\n"
+            "./ufacedetect --cascade=\"../../data/haarcascades/haarcascade_frontalface_alt.xml\" --nested-cascade=\"../../data/haarcascades/haarcascade_eye_tree_eyeglasses.xml\" --scale=1.3\n\n"
+            "During execution:\n\tHit any key to quit.\n"
+            "\tUsing OpenCV version " << CV_VERSION << "\n" << endl;
+}
+
+void detectAndDraw( UMat& img, Mat& canvas, CascadeClassifier& cascade,
+                    CascadeClassifier& nestedCascade,
+                    double scale, bool tryflip );
+
+int main( int argc, const char** argv )
+{
+    VideoCapture capture;
+    UMat frame, image;
+    Mat canvas;
+
+    string inputName;
+    bool tryflip;
+
+    CascadeClassifier cascade, nestedCascade;
+    double scale;
+
+    cv::CommandLineParser parser(argc, argv,
+        "{cascade|data/haarcascades/haarcascade_frontalface_alt.xml|}"
+        "{nested-cascade|data/haarcascades/haarcascade_eye_tree_eyeglasses.xml|}"
+        "{help h ||}{scale|1|}{try-flip||}{@filename||}"
+    );
+    if (parser.has("help"))
+    {
+        help();
+        return 0;
+    }
+    string cascadeName = samples::findFile(parser.get<string>("cascade"));
+    string nestedCascadeName = samples::findFileOrKeep(parser.get<string>("nested-cascade"));
+    scale = parser.get<double>("scale");
+    tryflip = parser.has("try-flip");
+    inputName = parser.get<string>("@filename");
+    if ( !parser.check())
+    {
+        parser.printErrors();
+        help();
+        return -1;
+    }
+
+    if ( !nestedCascade.load( nestedCascadeName ) )
+        cerr << "WARNING: Could not load classifier cascade for nested objects: " << nestedCascadeName << endl;
+    if( !cascade.load( cascadeName ) )
+    {
+        cerr << "ERROR: Could not load classifier cascade: " << cascadeName << endl;
+        help();
+        return -1;
+    }
+
+    cout << "old cascade: " << (cascade.isOldFormatCascade() ? "TRUE" : "FALSE") << endl;
+
+    if( inputName.empty() || (isdigit(inputName[0]) && inputName.size() == 1) )
+    {
+        int camera = inputName.empty() ? 0 : inputName[0] - '0';
+        if(!capture.open(camera))
+            cout << "Capture from camera #" <<  camera << " didn't work" << endl;
+    }
+    else
+    {
+        inputName = samples::findFileOrKeep(inputName);
+        imread(inputName, IMREAD_COLOR).copyTo(image);
+        if( image.empty() )
+        {
+            if(!capture.open( inputName ))
+                cout << "Could not read " << inputName << endl;
+        }
+    }
+
+    if( capture.isOpened() )
+    {
+        cout << "Video capturing has been started ..." << endl;
+        for(;;)
+        {
+            capture >> frame;
+            if( frame.empty() )
+                break;
+
+            detectAndDraw( frame, canvas, cascade, nestedCascade, scale, tryflip );
+
+            char c = (char)waitKey(10);
+            if( c == 27 || c == 'q' || c == 'Q' )
+                break;
+        }
+    }
+    else
+    {
+        cout << "Detecting face(s) in " << inputName << endl;
+        if( !image.empty() )
+        {
+            detectAndDraw( image, canvas, cascade, nestedCascade, scale, tryflip );
+            waitKey(0);
+        }
+        else if( !inputName.empty() )
+        {
+            /* assume it is a text file containing the
+            list of the image filenames to be processed - one per line */
+            FILE* f = fopen( inputName.c_str(), "rt" );
+            if( f )
+            {
+                char buf[1000+1];
+                while( fgets( buf, 1000, f ) )
+                {
+                    int len = (int)strlen(buf);
+                    while( len > 0 && isspace(buf[len-1]) )
+                        len--;
+                    buf[len] = '\0';
+                    cout << "file " << buf << endl;
+                    imread(samples::findFile(buf), IMREAD_COLOR).copyTo(image);
+                    if( !image.empty() )
+                    {
+                        detectAndDraw( image, canvas, cascade, nestedCascade, scale, tryflip );
+                        char c = (char)waitKey(0);
+                        if( c == 27 || c == 'q' || c == 'Q' )
+                            break;
+                    }
+                    else
+                    {
+                        cerr << "Aw snap, couldn't read image " << buf << endl;
+                    }
+                }
+                fclose(f);
+            }
+        }
+    }
+
+    return 0;
+}
+
+void detectAndDraw( UMat& img, Mat& canvas, CascadeClassifier& cascade,
+                    CascadeClassifier& nestedCascade,
+                    double scale, bool tryflip )
+{
+    double t = 0;
+    vector<Rect> faces, faces2;
+    const static Scalar colors[] =
+    {
+        Scalar(255,0,0),
+        Scalar(255,128,0),
+        Scalar(255,255,0),
+        Scalar(0,255,0),
+        Scalar(0,128,255),
+        Scalar(0,255,255),
+        Scalar(0,0,255),
+        Scalar(255,0,255)
+    };
+    static UMat gray, smallImg;
+
+    t = (double)getTickCount();
+
+    cvtColor( img, gray, COLOR_BGR2GRAY );
+    double fx = 1 / scale;
+    resize( gray, smallImg, Size(), fx, fx, INTER_LINEAR_EXACT );
+    equalizeHist( smallImg, smallImg );
+
+    cascade.detectMultiScale( smallImg, faces,
+        1.1, 3, 0
+        //|CASCADE_FIND_BIGGEST_OBJECT
+        //|CASCADE_DO_ROUGH_SEARCH
+        |CASCADE_SCALE_IMAGE,
+        Size(30, 30) );
+    if( tryflip )
+    {
+        flip(smallImg, smallImg, 1);
+        cascade.detectMultiScale( smallImg, faces2,
+                                 1.1, 2, 0
+                                 //|CASCADE_FIND_BIGGEST_OBJECT
+                                 //|CASCADE_DO_ROUGH_SEARCH
+                                 |CASCADE_SCALE_IMAGE,
+                                 Size(30, 30) );
+        for( vector<Rect>::const_iterator r = faces2.begin(); r != faces2.end(); ++r )
+        {
+            faces.push_back(Rect(smallImg.cols - r->x - r->width, r->y, r->width, r->height));
+        }
+    }
+    t = (double)getTickCount() - t;
+    img.copyTo(canvas);
+
+    double fps = getTickFrequency()/t;
+    static double avgfps = 0;
+    static int nframes = 0;
+    nframes++;
+    double alpha = nframes > 50 ? 0.01 : 1./nframes;
+    avgfps = avgfps*(1-alpha) + fps*alpha;
+
+    putText(canvas, cv::format("OpenCL: %s, fps: %.1f", ocl::useOpenCL() ? "ON" : "OFF", avgfps), Point(50, 30),
+            FONT_HERSHEY_SIMPLEX, 0.8, Scalar(0,255,0), 2);
+
+    for ( size_t i = 0; i < faces.size(); i++ )
+    {
+        Rect r = faces[i];
+        vector<Rect> nestedObjects;
+        Point center;
+        Scalar color = colors[i%8];
+        int radius;
+
+        double aspect_ratio = (double)r.width/r.height;
+        if( 0.75 < aspect_ratio && aspect_ratio < 1.3 )
+        {
+            center.x = cvRound((r.x + r.width*0.5)*scale);
+            center.y = cvRound((r.y + r.height*0.5)*scale);
+            radius = cvRound((r.width + r.height)*0.25*scale);
+            circle( canvas, center, radius, color, 3, 8, 0 );
+        }
+        else
+            rectangle( canvas, Point(cvRound(r.x*scale), cvRound(r.y*scale)),
+                       Point(cvRound((r.x + r.width-1)*scale), cvRound((r.y + r.height-1)*scale)),
+                       color, 3, 8, 0);
+        if( nestedCascade.empty() )
+            continue;
+        UMat smallImgROI = smallImg(r);
+        nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
+            1.1, 2, 0
+            //|CASCADE_FIND_BIGGEST_OBJECT
+            //|CASCADE_DO_ROUGH_SEARCH
+            //|CASCADE_DO_CANNY_PRUNING
+            |CASCADE_SCALE_IMAGE,
+            Size(30, 30) );
+
+        for ( size_t j = 0; j < nestedObjects.size(); j++ )
+        {
+            Rect nr = nestedObjects[j];
+            center.x = cvRound((r.x + nr.x + nr.width*0.5)*scale);
+            center.y = cvRound((r.y + nr.y + nr.height*0.5)*scale);
+            radius = cvRound((nr.width + nr.height)*0.25*scale);
+            circle( canvas, center, radius, color, 3, 8, 0 );
+        }
+    }
+    imshow( "result", canvas );
+}