Merge branch 4.x

samples/_winpack_run_python_sample.cmd

@@ -23,6 +23,8 @@ IF %ERRORLEVEL% EQU 0 (
   GOTO :PYTHON_FOUND
 )
 
+CALL :QUERY_PYTHON 3.11
+IF %ERRORLEVEL% EQU 0 GOTO :PYTHON_FOUND
 CALL :QUERY_PYTHON 3.10
 IF %ERRORLEVEL% EQU 0 GOTO :PYTHON_FOUND
 CALL :QUERY_PYTHON 3.9

samples/android/15-puzzle/gradle/AndroidManifest.xml

@@ -8,6 +8,7 @@
         android:label="@string/app_name">
 
         <activity
+            android:exported="true"
             android:name=".Puzzle15Activity"
             android:label="@string/app_name"
             android:screenOrientation="landscape"

samples/android/build.gradle.in

@@ -35,6 +35,7 @@ task clean(type: Delete) {
 //    }
 //}
 
+def opencv_strict_build_configuration = @ANDROID_STRICT_BUILD_CONFIGURATION@;
 
 gradle.afterProject { project ->
     if (project.pluginManager.hasPlugin('com.android.application')
@@ -90,5 +91,14 @@ gradle.afterProject { project ->
             }
         }
 
+        // Android Gradle Plugin (AGP) 3.5+ is required
+        // https://github.com/android/ndk-samples/wiki/Configure-NDK-Path
+        def isNdkVersionSupported = project.android.metaClass.getProperties().find { it.name == 'ndkVersion' } != null
+        if ((false || opencv_strict_build_configuration) && isNdkVersionSupported) {
+            gradle.println("Override ndkVersion for the project ${project.name}")
+            project.android {
+                ndkVersion '@ANDROID_NDK_REVISION@'
+            }
+        }
     }
 }

samples/android/camera-calibration/gradle/AndroidManifest.xml

@@ -7,7 +7,9 @@
         android:label="@string/app_name"
         android:icon="@drawable/icon">
 
-        <activity android:name="CameraCalibrationActivity"
+        <activity
+                  android:exported="true"
+                  android:name="CameraCalibrationActivity"
                   android:label="@string/app_name"
                   android:screenOrientation="landscape"
                   android:configChanges="keyboardHidden|orientation">

samples/android/color-blob-detection/gradle/AndroidManifest.xml

@@ -8,7 +8,9 @@
         android:icon="@drawable/icon"
         android:theme="@android:style/Theme.NoTitleBar.Fullscreen" >
 
-        <activity android:name="ColorBlobDetectionActivity"
+        <activity
+                  android:exported="true"
+                  android:name="ColorBlobDetectionActivity"
                   android:label="@string/app_name"
                   android:screenOrientation="landscape"
                   android:configChanges="keyboardHidden|orientation">

samples/android/face-detection/gradle/AndroidManifest.xml

@@ -7,7 +7,9 @@
         android:label="@string/app_name"
         android:icon="@drawable/icon">
 
-        <activity android:name="FdActivity"
+        <activity
+                  android:exported="true"
+                  android:name="FdActivity"
                   android:label="@string/app_name"
                   android:screenOrientation="landscape"
                   android:configChanges="keyboardHidden|orientation">

samples/android/image-manipulations/gradle/AndroidManifest.xml

@@ -7,7 +7,9 @@
         android:label="@string/app_name"
         android:icon="@drawable/icon">
 
-        <activity android:name="ImageManipulationsActivity"
+        <activity
+                  android:exported="true"
+                  android:name="ImageManipulationsActivity"
                   android:label="@string/app_name"
                   android:screenOrientation="landscape"
                   android:configChanges="keyboardHidden|orientation">

samples/android/mobilenet-objdetect/gradle/AndroidManifest.xml

@@ -10,8 +10,10 @@
         android:roundIcon="@mipmap/ic_launcher_round"
         android:supportsRtl="true"
         android:theme="@style/Theme.AppCompat.NoActionBar">  <!--Full screen mode-->
-        <activity android:name=".MainActivity"
-            android:screenOrientation="landscape">  <!--Screen orientation-->
+        <activity
+                  android:exported="true"
+                  android:name=".MainActivity"
+                  android:screenOrientation="landscape">  <!--Screen orientation-->
             <intent-filter>
                 <action android:name="android.intent.action.MAIN" />
                 <category android:name="android.intent.category.LAUNCHER" />

samples/android/tutorial-1-camerapreview/gradle/AndroidManifest.xml

@@ -8,7 +8,9 @@
         android:icon="@drawable/icon"
         android:theme="@android:style/Theme.NoTitleBar.Fullscreen" >
 
-        <activity android:name="Tutorial1Activity"
+        <activity
+                  android:exported="true"
+                  android:name="Tutorial1Activity"
                   android:label="@string/app_name"
                   android:screenOrientation="landscape"
                   android:configChanges="keyboardHidden|orientation">

samples/android/tutorial-2-mixedprocessing/gradle/AndroidManifest.xml

@@ -7,7 +7,9 @@
         android:label="@string/app_name"
         android:icon="@drawable/icon">
 
-        <activity android:name="Tutorial2Activity"
+        <activity
+                  android:exported="true"
+                  android:name="Tutorial2Activity"
                   android:label="@string/app_name"
                   android:screenOrientation="landscape"
                   android:configChanges="keyboardHidden|orientation">

samples/android/tutorial-3-cameracontrol/gradle/AndroidManifest.xml

@@ -7,7 +7,9 @@
         android:label="@string/app_name"
         android:icon="@drawable/icon">
 
-        <activity android:name="Tutorial3Activity"
+        <activity
+                  android:exported="true"
+                  android:name="Tutorial3Activity"
                   android:label="@string/app_name"
                   android:screenOrientation="landscape"
                   android:configChanges="keyboardHidden|orientation">

samples/android/tutorial-4-opencl/gradle/AndroidManifest.xml

@@ -1,31 +1,32 @@
 <?xml version="1.0" encoding="utf-8"?>
-<manifest xmlns:android="http://schemas.android.com/apk/res/android"
-    package="org.opencv.samples.tutorial4"
-    android:versionCode="1"
-    android:versionName="1.0" >
-
-    <uses-sdk
-        android:minSdkVersion="14"
-        android:targetSdkVersion="21" />
-
-    <uses-feature android:glEsVersion="0x00020000" android:required="true"/>
-    <uses-feature android:name="android.hardware.camera"/>
-    <uses-feature android:name="android.hardware.camera2" android:required="false"/>
-    <uses-permission android:name="android.permission.CAMERA"/>
-
-    <application
-        android:allowBackup="true"
-        android:icon="@drawable/icon">
-        <activity
-            android:name=".Tutorial4Activity"
-            android:label="@string/app_name"
-            android:screenOrientation="landscape"
-            android:configChanges="keyboardHidden|orientation">
-            <intent-filter>
-                <action android:name="android.intent.action.MAIN" />
-                <category android:name="android.intent.category.LAUNCHER" />
-            </intent-filter>
-        </activity>
-    </application>
-
-</manifest>
+<manifest xmlns:android="http://schemas.android.com/apk/res/android"
+    package="org.opencv.samples.tutorial4"
+    android:versionCode="1"
+    android:versionName="1.0" >
+
+    <uses-sdk
+        android:minSdkVersion="14"
+        android:targetSdkVersion="21" />
+
+    <uses-feature android:glEsVersion="0x00020000" android:required="true"/>
+    <uses-feature android:name="android.hardware.camera"/>
+    <uses-feature android:name="android.hardware.camera2" android:required="false"/>
+    <uses-permission android:name="android.permission.CAMERA"/>
+
+    <application
+        android:allowBackup="true"
+        android:icon="@drawable/icon">
+        <activity
+            android:exported="true"
+            android:name=".Tutorial4Activity"
+            android:label="@string/app_name"
+            android:screenOrientation="landscape"
+            android:configChanges="keyboardHidden|orientation">
+            <intent-filter>
+                <action android:name="android.intent.action.MAIN" />
+                <category android:name="android.intent.category.LAUNCHER" />
+            </intent-filter>
+        </activity>
+    </application>
+
+</manifest>

samples/cpp/calibration.cpp

@@ -39,9 +39,6 @@ const char * usage =
 "</images>\n"
 "</opencv_storage>\n";
 
-
-
-
 const char* liveCaptureHelp =
     "When the live video from camera is used as input, the following hot-keys may be used:\n"
         "  <ESC>, 'q' - quit the program\n"
@@ -60,19 +57,25 @@ static void help(char** argv)
         "                              #  of board views actually available)\n"
         "     [-d=<delay>]             # a minimum delay in ms between subsequent attempts to capture a next view\n"
         "                              # (used only for video capturing)\n"
-        "     [-s=<squareSize>]       # square size in some user-defined units (1 by default)\n"
+        "     [-s=<squareSize>]        # square size in some user-defined units (1 by default)\n"
         "     [-o=<out_camera_params>] # the output filename for intrinsic [and extrinsic] parameters\n"
         "     [-op]                    # write detected feature points\n"
         "     [-oe]                    # write extrinsic parameters\n"
         "     [-oo]                    # write refined 3D object points\n"
         "     [-zt]                    # assume zero tangential distortion\n"
-        "     [-a=<aspectRatio>]      # fix aspect ratio (fx/fy)\n"
+        "     [-a=<aspectRatio>]       # fix aspect ratio (fx/fy)\n"
         "     [-p]                     # fix the principal point at the center\n"
         "     [-v]                     # flip the captured images around the horizontal axis\n"
         "     [-V]                     # use a video file, and not an image list, uses\n"
         "                              # [input_data] string for the video file name\n"
         "     [-su]                    # show undistorted images after calibration\n"
-        "     [-ws=<number_of_pixel>]  # Half of search window for cornerSubPix (11 by default)\n"
+        "     [-ws=<number_of_pixel>]  # half of search window for cornerSubPix (11 by default)\n"
+        "     [-fx=<X focal length>]   # focal length in X-dir as an initial intrinsic guess (if this flag is used, fx, fy, cx, cy must be set)\n"
+        "     [-fy=<Y focal length>]   # focal length in Y-dir as an initial intrinsic guess (if this flag is used, fx, fy, cx, cy must be set)\n"
+        "     [-cx=<X center point>]   # camera center point in X-dir as an initial intrinsic guess (if this flag is used, fx, fy, cx, cy must be set)\n"
+        "     [-cy=<Y center point>]   # camera center point in Y-dir as an initial intrinsic guess (if this flag is used, fx, fy, cx, cy must be set)\n"
+        "     [-imshow-scale           # image resize scaling factor when displaying the results (must be >= 1)\n"
+        "     [-enable-k3=<0/1>        # to enable (1) or disable (0) K3 coefficient for the distortion model\n"
         "     [-dt=<distance>]         # actual distance between top-left and top-right corners of\n"
         "                              # the calibration grid. If this parameter is specified, a more\n"
         "                              # accurate calibration method will be used which may be better\n"
@@ -152,7 +155,6 @@ static bool runCalibration( vector<vector<Point2f> > imagePoints,
                     vector<Point3f>& newObjPoints,
                     double& totalAvgErr)
 {
-    cameraMatrix = Mat::eye(3, 3, CV_64F);
     if( flags & CALIB_FIX_ASPECT_RATIO )
         cameraMatrix.at<double>(0,0) = aspectRatio;
 
@@ -171,7 +173,7 @@ static bool runCalibration( vector<vector<Point2f> > imagePoints,
         iFixedPoint = boardSize.width - 1;
     rms = calibrateCameraRO(objectPoints, imagePoints, imageSize, iFixedPoint,
                             cameraMatrix, distCoeffs, rvecs, tvecs, newObjPoints,
-                            flags | CALIB_FIX_K3 | CALIB_USE_LU);
+                            flags | CALIB_USE_LU);
     printf("RMS error reported by calibrateCamera: %g\n", rms);
 
     bool ok = checkRange(cameraMatrix) && checkRange(distCoeffs);
@@ -192,7 +194,6 @@ static bool runCalibration( vector<vector<Point2f> > imagePoints,
     return ok;
 }
 
-
 static void saveCameraParams( const string& filename,
                        Size imageSize, Size boardSize,
                        float squareSize, float aspectRatio, int flags,
@@ -347,7 +348,6 @@ static bool runAndSave(const string& outputFilename,
     return ok;
 }
 
-
 int main( int argc, char** argv )
 {
     Size boardSize, imageSize;
@@ -376,6 +376,8 @@ int main( int argc, char** argv )
         "{help ||}{w||}{h||}{pt|chessboard|}{n|10|}{d|1000|}{s|1|}{o|out_camera_data.yml|}"
         "{op||}{oe||}{zt||}{a||}{p||}{v||}{V||}{su||}"
         "{oo||}{ws|11|}{dt||}"
+        "{fx||}{fy||}{cx||}{cy||}"
+        "{imshow-scale|1|}{enable-k3|0|}"
         "{@input_data|0|}");
     if (parser.has("help"))
     {
@@ -420,6 +422,23 @@ int main( int argc, char** argv )
     else
         inputFilename = parser.get<string>("@input_data");
     int winSize = parser.get<int>("ws");
+    cameraMatrix = Mat::eye(3, 3, CV_64F);
+    if (parser.has("fx") && parser.has("fy") && parser.has("cx") && parser.has("cy"))
+    {
+        cameraMatrix.at<double>(0,0) = parser.get<double>("fx");
+        cameraMatrix.at<double>(0,2) = parser.get<double>("cx");
+        cameraMatrix.at<double>(1,1) = parser.get<double>("fy");
+        cameraMatrix.at<double>(1,2) = parser.get<double>("cy");
+        flags |= CALIB_USE_INTRINSIC_GUESS;
+        std::cout << "Use the following camera matrix as an initial guess:\n" << cameraMatrix << std::endl;
+    }
+    int viewScaleFactor = parser.get<int>("imshow-scale");
+    bool useK3 = parser.get<bool>("enable-k3");
+    std::cout << "Use K3 distortion coefficient? " << useK3 << std::endl;
+    if (!useK3)
+    {
+        flags |= CALIB_FIX_K3;
+    }
     float grid_width = squareSize * (boardSize.width - 1);
     bool release_object = false;
     if (parser.has("dt")) {
@@ -555,8 +574,17 @@ int main( int argc, char** argv )
             Mat temp = view.clone();
             undistort(temp, view, cameraMatrix, distCoeffs);
         }
+        if (viewScaleFactor > 1)
+        {
+            Mat viewScale;
+            resize(view, viewScale, Size(), 1.0/viewScaleFactor, 1.0/viewScaleFactor, INTER_AREA);
+            imshow("Image View", viewScale);
+        }
+        else
+        {
+            imshow("Image View", view);
+        }
 
-        imshow("Image View", view);
         char key = (char)waitKey(capture.isOpened() ? 50 : 500);
 
         if( key == 27 )
@@ -597,9 +625,17 @@ int main( int argc, char** argv )
             view = imread(imageList[i], 1);
             if(view.empty())
                 continue;
-            //undistort( view, rview, cameraMatrix, distCoeffs, cameraMatrix );
             remap(view, rview, map1, map2, INTER_LINEAR);
-            imshow("Image View", rview);
+            if (viewScaleFactor > 1)
+            {
+                Mat rviewScale;
+                resize(rview, rviewScale, Size(), 1.0/viewScaleFactor, 1.0/viewScaleFactor, INTER_AREA);
+                imshow("Image View", rviewScale);
+            }
+            else
+            {
+                imshow("Image View", rview);
+            }
             char c = (char)waitKey();
             if( c == 27 || c == 'q' || c == 'Q' )
                 break;

samples/cpp/tutorial_code/ImgTrans/generalizedHoughTransform.cpp

@@ -0,0 +1,108 @@
+/**
+  @file generalizedHoughTransform.cpp
+  @author Markus Heck
+  @brief Detects an object, given by a template, in an image using GeneralizedHoughBallard and GeneralizedHoughGuil.
+*/
+
+#include "opencv2/highgui.hpp"
+#include "opencv2/imgproc.hpp"
+
+using namespace cv;
+using namespace std;
+
+int main() {
+    //! [generalized-hough-transform-load-and-setup]
+//  load source image and grayscale template
+    Mat image = imread("images/generalized_hough_mini_image.jpg");
+    Mat templ = imread("images/generalized_hough_mini_template.jpg", IMREAD_GRAYSCALE);
+
+//  create grayscale image
+    Mat grayImage;
+    cvtColor(image, grayImage, COLOR_RGB2GRAY);
+
+//  create variable for location, scale and rotation of detected templates
+    vector<Vec4f> positionBallard, positionGuil;
+
+//  template width and height
+    int w = templ.cols;
+    int h = templ.rows;
+    //! [generalized-hough-transform-load-and-setup]
+
+
+    //! [generalized-hough-transform-setup-parameters]
+//  create ballard and set options
+    Ptr<GeneralizedHoughBallard> ballard = createGeneralizedHoughBallard();
+    ballard->setMinDist(10);
+    ballard->setLevels(360);
+    ballard->setDp(2);
+    ballard->setMaxBufferSize(1000);
+    ballard->setVotesThreshold(40);
+
+    ballard->setCannyLowThresh(30);
+    ballard->setCannyHighThresh(110);
+    ballard->setTemplate(templ);
+
+
+//  create guil and set options
+    Ptr<GeneralizedHoughGuil> guil = createGeneralizedHoughGuil();
+    guil->setMinDist(10);
+    guil->setLevels(360);
+    guil->setDp(3);
+    guil->setMaxBufferSize(1000);
+
+    guil->setMinAngle(0);
+    guil->setMaxAngle(360);
+    guil->setAngleStep(1);
+    guil->setAngleThresh(1500);
+
+    guil->setMinScale(0.5);
+    guil->setMaxScale(2.0);
+    guil->setScaleStep(0.05);
+    guil->setScaleThresh(50);
+
+    guil->setPosThresh(10);
+
+    guil->setCannyLowThresh(30);
+    guil->setCannyHighThresh(110);
+
+    guil->setTemplate(templ);
+    //! [generalized-hough-transform-setup-parameters]
+
+
+    //! [generalized-hough-transform-run]
+//  execute ballard detection
+    ballard->detect(grayImage, positionBallard);
+//  execute guil detection
+    guil->detect(grayImage, positionGuil);
+    //! [generalized-hough-transform-run]
+
+
+    //! [generalized-hough-transform-draw-results]
+//  draw ballard
+    for (vector<Vec4f>::iterator iter = positionBallard.begin(); iter != positionBallard.end(); ++iter) {
+        RotatedRect rRect = RotatedRect(Point2f((*iter)[0], (*iter)[1]),
+                                        Size2f(w * (*iter)[2], h * (*iter)[2]),
+                                        (*iter)[3]);
+        Point2f vertices[4];
+        rRect.points(vertices);
+        for (int i = 0; i < 4; i++)
+            line(image, vertices[i], vertices[(i + 1) % 4], Scalar(255, 0, 0), 6);
+    }
+
+//  draw guil
+    for (vector<Vec4f>::iterator iter = positionGuil.begin(); iter != positionGuil.end(); ++iter) {
+        RotatedRect rRect = RotatedRect(Point2f((*iter)[0], (*iter)[1]),
+                                        Size2f(w * (*iter)[2], h * (*iter)[2]),
+                                        (*iter)[3]);
+        Point2f vertices[4];
+        rRect.points(vertices);
+        for (int i = 0; i < 4; i++)
+            line(image, vertices[i], vertices[(i + 1) % 4], Scalar(0, 255, 0), 2);
+    }
+
+    imshow("result_img", image);
+    waitKey();
+    //! [generalized-hough-transform-draw-results]
+
+    return EXIT_SUCCESS;
+}

samples/cpp/tutorial_code/video/meanshift/camshift.cpp

@@ -58,7 +58,7 @@ int main(int argc, char **argv)
     calcHist(&hsv_roi, 1, channels, mask, roi_hist, 1, histSize, range);
     normalize(roi_hist, roi_hist, 0, 255, NORM_MINMAX);
 
-    // Setup the termination criteria, either 10 iteration or move by atleast 1 pt
+    // Setup the termination criteria, either 10 iteration or move by at least 1 pt
     TermCriteria term_crit(TermCriteria::EPS | TermCriteria::COUNT, 10, 1);
 
     while(true){

samples/cpp/tutorial_code/video/meanshift/meanshift.cpp

@@ -58,7 +58,7 @@ int main(int argc, char **argv)
     calcHist(&hsv_roi, 1, channels, mask, roi_hist, 1, histSize, range);
     normalize(roi_hist, roi_hist, 0, 255, NORM_MINMAX);
 
-    // Setup the termination criteria, either 10 iteration or move by atleast 1 pt
+    // Setup the termination criteria, either 10 iteration or move by at least 1 pt
     TermCriteria term_crit(TermCriteria::EPS | TermCriteria::COUNT, 10, 1);
 
     while(true){

samples/data/dnn/object_detection_classes_yolov4.txt

@@ -1,8 +1,8 @@
 person
 bicycle
 car
-motorcycle
-airplane
+motorbike
+aeroplane
 bus
 train
 truck
@@ -55,12 +55,12 @@ pizza
 donut
 cake
 chair
-couch
-potted plant
+sofa
+pottedplant
 bed
-dining table
+diningtable
 toilet
-tv
+tvmonitor
 laptop
 mouse
 remote

samples/directx/CMakeLists.txt

@@ -19,4 +19,16 @@ foreach(sample_filename ${all_samples})
   ocv_define_sample(tgt ${sample_filename} directx)
   ocv_target_link_libraries(${tgt} PRIVATE ${OPENCV_LINKER_LIBS} ${OPENCV_DIRECTX_SAMPLES_REQUIRED_DEPS})
   ocv_target_link_libraries(${tgt} PRIVATE "gdi32")
+  if(sample_filename STREQUAL "d3d9_interop.cpp")
+    ocv_target_link_libraries(${tgt} PRIVATE d3d9)
+  endif()
+  if(sample_filename STREQUAL "d3d9ex_interop.cpp")
+    ocv_target_link_libraries(${tgt} PRIVATE d3d9)
+  endif()
+  if(sample_filename STREQUAL "d3d10_interop.cpp")
+    ocv_target_link_libraries(${tgt} PRIVATE d3d10)
+  endif()
+  if(sample_filename STREQUAL "d3d11_interop.cpp")
+    ocv_target_link_libraries(${tgt} PRIVATE d3d11)
+  endif()
 endforeach()

samples/directx/d3d10_interop.cpp

@@ -17,7 +17,6 @@
 
 #include "d3dsample.hpp"
 
-#pragma comment (lib, "d3d10.lib")
 
 class D3D10WinApp : public D3DSample
 {

samples/directx/d3d11_interop.cpp

@@ -17,7 +17,6 @@
 
 #include "d3dsample.hpp"
 
-#pragma comment (lib, "d3d11.lib")
 
 class D3D11WinApp : public D3DSample
 {

samples/directx/d3d9_interop.cpp

@@ -17,7 +17,6 @@
 
 #include "d3dsample.hpp"
 
-#pragma comment (lib, "d3d9.lib")
 
 
 class D3D9WinApp : public D3DSample

samples/directx/d3d9ex_interop.cpp

@@ -17,7 +17,6 @@
 
 #include "d3dsample.hpp"
 
-#pragma comment (lib, "d3d9.lib")
 
 
 class D3D9ExWinApp : public D3DSample

samples/dnn/models.yml

@@ -23,16 +23,16 @@ opencv_fd:
 # Might be used for all YOLOv2, TinyYolov2, YOLOv3, YOLOv4 and TinyYolov4
 yolo:
   load_info:
-    url: "https://pjreddie.com/media/files/yolov3.weights"
-    sha1: "520878f12e97cf820529daea502acca380f1cb8e"
-  model: "yolov3.weights"
-  config: "yolov3.cfg"
+    url: "https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.weights"
+    sha1: "0143deb6c46fcc7f74dd35bf3c14edc3784e99ee"
+  model: "yolov4.weights"
+  config: "yolov4.cfg"
   mean: [0, 0, 0]
   scale: 0.00392
   width: 416
   height: 416
   rgb: true
-  classes: "object_detection_classes_yolov3.txt"
+  classes: "object_detection_classes_yolov4.txt"
   sample: "object_detection"
 
 tiny-yolo-voc:

samples/dnn/nanotrack_tracker.cpp

@@ -0,0 +1,183 @@
+// NanoTrack
+// Link to original inference code: https://github.com/HonglinChu/NanoTrack
+// Link to original training repo: https://github.com/HonglinChu/SiamTrackers/tree/master/NanoTrack
+// backBone model: https://github.com/HonglinChu/SiamTrackers/blob/master/NanoTrack/models/onnx/nanotrack_backbone_sim.onnx
+// headNeck model: https://github.com/HonglinChu/SiamTrackers/blob/master/NanoTrack/models/onnx/nanotrack_head_sim.onnx
+
+#include <iostream>
+#include <cmath>
+
+#include <opencv2/dnn.hpp>
+#include <opencv2/imgproc.hpp>
+#include <opencv2/highgui.hpp>
+#include <opencv2/video.hpp>
+
+using namespace cv;
+using namespace cv::dnn;
+
+const char *keys =
+        "{ help     h  |   | Print help message }"
+        "{ input    i  |   | Full path to input video folder, the specific camera index. (empty for camera 0) }"
+        "{ backbone    | backbone.onnx | Path to onnx model of backbone.onnx}"
+        "{ headneck    | headneck.onnx | Path to onnx model of headneck.onnx }"
+        "{ backend     | 0 | Choose one of computation backends: "
+                            "0: automatically (by default), "
+                            "1: Halide language (http://halide-lang.org/), "
+                            "2: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
+                            "3: OpenCV implementation, "
+                            "4: VKCOM, "
+                            "5: CUDA },"
+        "{ target      | 0 | Choose one of target computation devices: "
+                            "0: CPU target (by default), "
+                            "1: OpenCL, "
+                            "2: OpenCL fp16 (half-float precision), "
+                            "3: VPU, "
+                            "4: Vulkan, "
+                            "6: CUDA, "
+                            "7: CUDA fp16 (half-float preprocess) }"
+;
+
+static
+int run(int argc, char** argv)
+{
+    // Parse command line arguments.
+    CommandLineParser parser(argc, argv, keys);
+
+    if (parser.has("help"))
+    {
+        parser.printMessage();
+        return 0;
+    }
+
+    std::string inputName = parser.get<String>("input");
+    std::string backbone = parser.get<String>("backbone");
+    std::string headneck = parser.get<String>("headneck");
+    int backend = parser.get<int>("backend");
+    int target = parser.get<int>("target");
+
+    Ptr<TrackerNano> tracker;
+    try
+    {
+        TrackerNano::Params params;
+        params.backbone = samples::findFile(backbone);
+        params.neckhead = samples::findFile(headneck);
+        params.backend = backend;
+        params.target = target;
+        tracker = TrackerNano::create(params);
+    }
+    catch (const cv::Exception& ee)
+    {
+        std::cerr << "Exception: " << ee.what() << std::endl;
+        std::cout << "Can't load the network by using the following files:" << std::endl;
+        std::cout << "backbone : " << backbone << std::endl;
+        std::cout << "headneck : " << headneck << std::endl;
+        return 2;
+    }
+
+    const std::string winName = "NanoTrack";
+    namedWindow(winName, WINDOW_AUTOSIZE);
+
+    // Open a video file or an image file or a camera stream.
+    VideoCapture cap;
+
+    if (inputName.empty() || (isdigit(inputName[0]) && inputName.size() == 1))
+    {
+        int c = inputName.empty() ? 0 : inputName[0] - '0';
+        std::cout << "Trying to open camera #" << c << " ..." << std::endl;
+        if (!cap.open(c))
+        {
+            std::cout << "Capture from camera #" << c << " didn't work. Specify -i=<video> parameter to read from video file" << std::endl;
+            return 2;
+        }
+    }
+    else if (inputName.size())
+    {
+        inputName = samples::findFileOrKeep(inputName);
+        if (!cap.open(inputName))
+        {
+            std::cout << "Could not open: " << inputName << std::endl;
+            return 2;
+        }
+    }
+
+    // Read the first image.
+    Mat image;
+    cap >> image;
+    if (image.empty())
+    {
+        std::cerr << "Can't capture frame!" << std::endl;
+        return 2;
+    }
+
+    Mat image_select = image.clone();
+    putText(image_select, "Select initial bounding box you want to track.", Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
+    putText(image_select, "And Press the ENTER key.", Point(0, 35), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
+
+    Rect selectRect = selectROI(winName, image_select);
+    std::cout << "ROI=" << selectRect << std::endl;
+
+    tracker->init(image, selectRect);
+
+    TickMeter tickMeter;
+
+    for (int count = 0; ; ++count)
+    {
+        cap >> image;
+        if (image.empty())
+        {
+            std::cerr << "Can't capture frame " << count << ". End of video stream?" << std::endl;
+            break;
+        }
+
+        Rect rect;
+
+        tickMeter.start();
+        bool ok = tracker->update(image, rect);
+        tickMeter.stop();
+
+        float score = tracker->getTrackingScore();
+
+        std::cout << "frame " << count <<
+            ": predicted score=" << score <<
+            "  rect=" << rect <<
+            "  time=" << tickMeter.getTimeMilli() << "ms" <<
+            std::endl;
+
+        Mat render_image = image.clone();
+
+        if (ok)
+        {
+            rectangle(render_image, rect, Scalar(0, 255, 0), 2);
+
+            std::string timeLabel = format("Inference time: %.2f ms", tickMeter.getTimeMilli());
+            std::string scoreLabel = format("Score: %f", score);
+            putText(render_image, timeLabel, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
+            putText(render_image, scoreLabel, Point(0, 35), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
+        }
+
+        imshow(winName, render_image);
+
+        tickMeter.reset();
+
+        int c = waitKey(1);
+        if (c == 27 /*ESC*/)
+            break;
+    }
+
+    std::cout << "Exit" << std::endl;
+    return 0;
+}
+
+
+int main(int argc, char **argv)
+{
+    try
+    {
+        return run(argc, argv);
+    }
+    catch (const std::exception& e)
+    {
+        std::cerr << "FATAL: C++ exception: " << e.what() << std::endl;
+        return 1;
+    }
+}

samples/gpu/video_reader.cpp

@@ -22,65 +22,41 @@ int main(int argc, const char* argv[])
     const std::string fname(argv[1]);
 
     cv::namedWindow("CPU", cv::WINDOW_NORMAL);
+#if defined(HAVE_OPENGL)
     cv::namedWindow("GPU", cv::WINDOW_OPENGL);
     cv::cuda::setGlDevice();
+#else
+    cv::namedWindow("GPU", cv::WINDOW_NORMAL);
+#endif
 
+    cv::TickMeter tm;
     cv::Mat frame;
     cv::VideoCapture reader(fname);
+    for (;;)
+    {
+        if (!reader.read(frame))
+            break;
+        cv::imshow("CPU", frame);
+        if (cv::waitKey(3) > 0)
+            break;
+    }
 
     cv::cuda::GpuMat d_frame;
     cv::Ptr<cv::cudacodec::VideoReader> d_reader = cv::cudacodec::createVideoReader(fname);
-
-    cv::TickMeter tm;
-    std::vector<double> cpu_times;
-    std::vector<double> gpu_times;
-
-    int gpu_frame_count=0, cpu_frame_count=0;
-
     for (;;)
     {
-        tm.reset(); tm.start();
-        if (!reader.read(frame))
-            break;
-        tm.stop();
-        cpu_times.push_back(tm.getTimeMilli());
-        cpu_frame_count++;
-
-        cv::imshow("CPU", frame);
-
-        if (cv::waitKey(3) > 0)
-            break;
-    }
-
-    for (;;)
-    {
-        tm.reset(); tm.start();
         if (!d_reader->nextFrame(d_frame))
             break;
-        tm.stop();
-        gpu_times.push_back(tm.getTimeMilli());
-        gpu_frame_count++;
-
-        cv::imshow("GPU", d_frame);
-
+#if defined(HAVE_OPENGL)
+        cv::imshow("GPU", cv::ogl::Texture2D(d_frame));
+#else
+        d_frame.download(frame);
+        cv::imshow("GPU", frame);
+#endif
         if (cv::waitKey(3) > 0)
             break;
     }
 
-    if (!cpu_times.empty() && !gpu_times.empty())
-    {
-        std::cout << std::endl << "Results:" << std::endl;
-
-        std::sort(cpu_times.begin(), cpu_times.end());
-        std::sort(gpu_times.begin(), gpu_times.end());
-
-        double cpu_avg = std::accumulate(cpu_times.begin(), cpu_times.end(), 0.0) / cpu_times.size();
-        double gpu_avg = std::accumulate(gpu_times.begin(), gpu_times.end(), 0.0) / gpu_times.size();
-
-        std::cout << "CPU : Avg : " << cpu_avg << " ms FPS : " << 1000.0 / cpu_avg << " Frames " << cpu_frame_count << std::endl;
-        std::cout << "GPU : Avg : " << gpu_avg << " ms FPS : " << 1000.0 / gpu_avg << " Frames " << gpu_frame_count << std::endl;
-    }
-
     return 0;
 }
 

samples/gpu/video_writer.cpp

@@ -2,7 +2,7 @@
 
 #include "opencv2/opencv_modules.hpp"
 
-#if defined(HAVE_OPENCV_CUDACODEC) && defined(_WIN32)
+#if defined(HAVE_OPENCV_CUDACODEC)
 
 #include <vector>
 #include <numeric>
@@ -20,7 +20,7 @@ int main(int argc, const char* argv[])
         return -1;
     }
 
-    const double FPS = 25.0;
+    constexpr double fps = 25.0;
 
     cv::VideoCapture reader(argv[1]);
 
@@ -37,17 +37,12 @@ int main(int argc, const char* argv[])
 
     cv::Mat frame;
     cv::cuda::GpuMat d_frame;
-
-    std::vector<double> cpu_times;
-    std::vector<double> gpu_times;
-    TickMeter tm;
+    cv::cuda::Stream stream;
 
     for (int i = 1;; ++i)
     {
         std::cout << "Read " << i << " frame" << std::endl;
-
         reader >> frame;
-
         if (frame.empty())
         {
             std::cout << "Stop" << std::endl;
@@ -57,47 +52,27 @@ int main(int argc, const char* argv[])
         if (!writer.isOpened())
         {
             std::cout << "Frame Size : " << frame.cols << "x" << frame.rows << std::endl;
-
             std::cout << "Open CPU Writer" << std::endl;
-
-            if (!writer.open("output_cpu.avi", cv::VideoWriter::fourcc('X', 'V', 'I', 'D'), FPS, frame.size()))
+            const String outputFilename = "output_cpu.avi";
+            if (!writer.open(outputFilename, cv::VideoWriter::fourcc('X', 'V', 'I', 'D'), fps, frame.size()))
                 return -1;
+            std::cout << "Writing to " << outputFilename << std::endl;
         }
 
         if (d_writer.empty())
         {
             std::cout << "Open CUDA Writer" << std::endl;
-
-            const cv::String outputFilename = "output_gpu.avi";
-            d_writer = cv::cudacodec::createVideoWriter(outputFilename, frame.size(), FPS);
+            const cv::String outputFilename = "output_gpu.h264";
+            d_writer = cv::cudacodec::createVideoWriter(outputFilename, frame.size(), cv::cudacodec::Codec::H264, fps, cv::cudacodec::ColorFormat::BGR, 0, stream);
+            std::cout << "Writing to " << outputFilename << std::endl;
         }
 
-        d_frame.upload(frame);
-
+        d_frame.upload(frame, stream);
         std::cout << "Write " << i << " frame" << std::endl;
-
-        tm.reset(); tm.start();
         writer.write(frame);
-        tm.stop();
-        cpu_times.push_back(tm.getTimeMilli());
-
-        tm.reset(); tm.start();
         d_writer->write(d_frame);
-        tm.stop();
-        gpu_times.push_back(tm.getTimeMilli());
     }
 
-    std::cout << std::endl << "Results:" << std::endl;
-
-    std::sort(cpu_times.begin(), cpu_times.end());
-    std::sort(gpu_times.begin(), gpu_times.end());
-
-    double cpu_avg = std::accumulate(cpu_times.begin(), cpu_times.end(), 0.0) / cpu_times.size();
-    double gpu_avg = std::accumulate(gpu_times.begin(), gpu_times.end(), 0.0) / gpu_times.size();
-
-    std::cout << "CPU [XVID] : Avg : " << cpu_avg << " ms FPS : " << 1000.0 / cpu_avg << std::endl;
-    std::cout << "GPU [H264] : Avg : " << gpu_avg << " ms FPS : " << 1000.0 / gpu_avg << std::endl;
-
     return 0;
 }
 

samples/java/tutorial_code/video/meanshift/CamshiftDemo.java

@@ -35,7 +35,7 @@ class Camshift {
         Imgproc.calcHist(Arrays.asList(hsv_roi), channels, mask, roi_hist, histSize, range);
         Core.normalize(roi_hist, roi_hist, 0, 255, Core.NORM_MINMAX);
 
-        // Setup the termination criteria, either 10 iteration or move by atleast 1 pt
+        // Setup the termination criteria, either 10 iteration or move by at least 1 pt
         TermCriteria term_crit = new TermCriteria(TermCriteria.EPS | TermCriteria.COUNT, 10, 1);
 
         while (true) {

samples/java/tutorial_code/video/meanshift/MeanshiftDemo.java

@@ -34,7 +34,7 @@ class Meanshift {
         Imgproc.calcHist(Arrays.asList(hsv_roi), channels, mask, roi_hist, histSize, range);
         Core.normalize(roi_hist, roi_hist, 0, 255, Core.NORM_MINMAX);
 
-        // Setup the termination criteria, either 10 iteration or move by atleast 1 pt
+        // Setup the termination criteria, either 10 iteration or move by at least 1 pt
         TermCriteria term_crit = new TermCriteria(TermCriteria.EPS | TermCriteria.COUNT, 10, 1);
 
         while (true) {

samples/opengl/opengl_interop.cpp

@@ -27,12 +27,6 @@
 
 #include "winapp.hpp"
 
-#if defined(_WIN32)
-# pragma comment(lib, "opengl32.lib")
-# pragma comment(lib, "glu32.lib")
-#endif
-
-
 class GLWinApp : public WinApp
 {
 public:

samples/python/tracker.py

@@ -9,6 +9,9 @@ For DaSiamRPN:
     network:     https://www.dropbox.com/s/rr1lk9355vzolqv/dasiamrpn_model.onnx?dl=0
     kernel_r1:   https://www.dropbox.com/s/999cqx5zrfi7w4p/dasiamrpn_kernel_r1.onnx?dl=0
     kernel_cls1: https://www.dropbox.com/s/qvmtszx5h339a0w/dasiamrpn_kernel_cls1.onnx?dl=0
+For NanoTrack:
+    nanotrack_backbone: https://github.com/HonglinChu/SiamTrackers/blob/master/NanoTrack/models/nanotrackv2/nanotrack_backbone_sim.onnx
+    nanotrack_headneck: https://github.com/HonglinChu/SiamTrackers/blob/master/NanoTrack/models/nanotrackv2/nanotrack_head_sim.onnx
 
 USAGE:
     tracker.py [-h] [--input INPUT] [--tracker_algo TRACKER_ALGO]
@@ -18,6 +21,7 @@ USAGE:
                     [--dasiamrpn_kernel_cls1 DASIAMRPN_KERNEL_CLS1]
                     [--dasiamrpn_backend DASIAMRPN_BACKEND]
                     [--dasiamrpn_target DASIAMRPN_TARGET]
+                    [--nanotrack_backbone NANOTRACK_BACKEND] [--nanotrack_headneck NANOTRACK_TARGET]
 '''
 
 # Python 2/3 compatibility
@@ -52,8 +56,13 @@ class App(object):
             params.kernel_cls1 = self.args.dasiamrpn_kernel_cls1
             params.kernel_r1 = self.args.dasiamrpn_kernel_r1
             tracker = cv.TrackerDaSiamRPN_create(params)
+        elif self.trackerAlgorithm == 'nanotrack':
+            params = cv.TrackerNano_Params()
+            params.backbone = args.nanotrack_backbone
+            params.neckhead = args.nanotrack_headneck
+            tracker = cv.TrackerNano_create(params)
         else:
-            sys.exit("Tracker {} is not recognized. Please use one of three available: mil, goturn, dasiamrpn.".format(self.trackerAlgorithm))
+            sys.exit("Tracker {} is not recognized. Please use one of three available: mil, goturn, dasiamrpn, nanotrack.".format(self.trackerAlgorithm))
         return tracker
 
     def initializeTracker(self, image):
@@ -117,12 +126,14 @@ if __name__ == '__main__':
     print(__doc__)
     parser = argparse.ArgumentParser(description="Run tracker")
     parser.add_argument("--input", type=str, default="vtest.avi", help="Path to video source")
-    parser.add_argument("--tracker_algo", type=str, default="mil", help="One of available tracking algorithms: mil, goturn, dasiamrpn")
+    parser.add_argument("--tracker_algo", type=str, default="nanotrack", help="One of available tracking algorithms: mil, goturn, dasiamrpn, nanotrack")
     parser.add_argument("--goturn", type=str, default="goturn.prototxt", help="Path to GOTURN architecture")
     parser.add_argument("--goturn_model", type=str, default="goturn.caffemodel", help="Path to GOTERN model")
     parser.add_argument("--dasiamrpn_net", type=str, default="dasiamrpn_model.onnx", help="Path to onnx model of DaSiamRPN net")
     parser.add_argument("--dasiamrpn_kernel_r1", type=str, default="dasiamrpn_kernel_r1.onnx", help="Path to onnx model of DaSiamRPN kernel_r1")
     parser.add_argument("--dasiamrpn_kernel_cls1", type=str, default="dasiamrpn_kernel_cls1.onnx", help="Path to onnx model of DaSiamRPN kernel_cls1")
+    parser.add_argument("--nanotrack_backbone", type=str, default="nanotrack_backbone_sim.onnx", help="Path to onnx model of NanoTrack backBone")
+    parser.add_argument("--nanotrack_headneck", type=str, default="nanotrack_head_sim.onnx", help="Path to onnx model of NanoTrack headNeck")
 
     args = parser.parse_args()
     App(args).run()

samples/winrt/ImageManipulations/MainPage.xaml.cpp

@@ -91,7 +91,7 @@ void MainPage::InvalidateSize()
         // We have different widths to use depending on the view state
         if (ApplicationView::Value != ApplicationViewState::Snapped)
         {
-            // Make us as big as the the left over space, factoring in the ListBox width, the ListBox margins.
+            // Make us as big as the left over space, factoring in the ListBox width, the ListBox margins.
             // and the LayoutRoot's margins
             InputSection->Width = ((availableWidth) -
                 (layoutRootMarginLeft + layoutRootMarginRight + listBoxMarginLeft + listBoxMarginRight));