Merge branch 4.x

samples/dnn/face_detect.cpp

@@ -44,8 +44,8 @@ int main(int argc, char** argv)
         "{image2 i2         |            | Path to the input image2. When image1 and image2 parameters given then the program try to find a face on both images and runs face recognition algorithm}"
         "{video v           | 0          | Path to the input video}"
         "{scale sc          | 1.0        | Scale factor used to resize input video frames}"
-        "{fd_model fd       | yunet.onnx | Path to the model. Download yunet.onnx in https://github.com/ShiqiYu/libfacedetection.train/tree/master/tasks/task1/onnx }"
-        "{fr_model fr       | face_recognizer_fast.onnx | Path to the face recognition model. Download the model at https://drive.google.com/file/d/1ClK9WiB492c5OZFKveF3XiHCejoOxINW/view}"
+        "{fd_model fd       | face_detection_yunet_2021dec.onnx| Path to the model. Download yunet.onnx in https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet}"
+        "{fr_model fr       | face_recognition_sface_2021dec.onnx | Path to the face recognition model. Download the model at https://github.com/opencv/opencv_zoo/tree/master/models/face_recognition_sface}"
         "{score_threshold   | 0.9        | Filter out faces of score < score_threshold}"
         "{nms_threshold     | 0.3        | Suppress bounding boxes of iou >= nms_threshold}"
         "{top_k             | 5000       | Keep top_k bounding boxes before NMS}"
@@ -65,6 +65,7 @@ int main(int argc, char** argv)
     int topK = parser.get<int>("top_k");
 
     bool save = parser.get<bool>("save");
+    float scale = parser.get<float>("scale");
 
     double cosine_similar_thresh = 0.363;
     double l2norm_similar_thresh = 1.128;
@@ -87,6 +88,9 @@ int main(int argc, char** argv)
             return 2;
         }
 
+        int imageWidth = int(image1.cols * scale);
+        int imageHeight = int(image1.rows * scale);
+        resize(image1, image1, Size(imageWidth, imageHeight));
         tm.start();
 
         //! [inference]
@@ -199,7 +203,6 @@ int main(int argc, char** argv)
     else
     {
         int frameWidth, frameHeight;
-        float scale = parser.get<float>("scale");
         VideoCapture capture;
         std::string video = parser.get<string>("video");
         if (video.size() == 1 && isdigit(video[0]))

samples/dnn/face_detect.py

@@ -16,8 +16,8 @@ parser.add_argument('--image1', '-i1', type=str, help='Path to the input image1.
 parser.add_argument('--image2', '-i2', type=str, help='Path to the input image2. When image1 and image2 parameters given then the program try to find a face on both images and runs face recognition algorithm.')
 parser.add_argument('--video', '-v', type=str, help='Path to the input video.')
 parser.add_argument('--scale', '-sc', type=float, default=1.0, help='Scale factor used to resize input video frames.')
-parser.add_argument('--face_detection_model', '-fd', type=str, default='yunet.onnx', help='Path to the face detection model. Download the model at https://github.com/ShiqiYu/libfacedetection.train/tree/master/tasks/task1/onnx.')
-parser.add_argument('--face_recognition_model', '-fr', type=str, default='face_recognizer_fast.onnx', help='Path to the face recognition model. Download the model at https://drive.google.com/file/d/1ClK9WiB492c5OZFKveF3XiHCejoOxINW/view.')
+parser.add_argument('--face_detection_model', '-fd', type=str, default='face_detection_yunet_2021dec.onnx', help='Path to the face detection model. Download the model at https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet')
+parser.add_argument('--face_recognition_model', '-fr', type=str, default='face_recognition_sface_2021dec.onnx', help='Path to the face recognition model. Download the model at https://github.com/opencv/opencv_zoo/tree/master/models/face_recognition_sface')
 parser.add_argument('--score_threshold', type=float, default=0.9, help='Filtering out faces of score < score_threshold.')
 parser.add_argument('--nms_threshold', type=float, default=0.3, help='Suppress bounding boxes of iou >= nms_threshold.')
 parser.add_argument('--top_k', type=int, default=5000, help='Keep top_k bounding boxes before NMS.')
@@ -56,11 +56,15 @@ if __name__ == '__main__':
     # If input is an image
     if args.image1 is not None:
         img1 = cv.imread(cv.samples.findFile(args.image1))
+        img1Width = int(img1.shape[1]*args.scale)
+        img1Height = int(img1.shape[0]*args.scale)
 
+        img1 = cv.resize(img1, (img1Width, img1Height))
         tm.start()
+
         ## [inference]
         # Set input size before inference
-        detector.setInputSize((img1.shape[1], img1.shape[0]))
+        detector.setInputSize((img1Width, img1Height))
 
         faces1 = detector.detect(img1)
         ## [inference]

samples/dnn/text_detection.py

@@ -195,7 +195,7 @@ def main():
         indices = cv.dnn.NMSBoxesRotated(boxes, confidences, confThreshold, nmsThreshold)
         for i in indices:
             # get 4 corners of the rotated rect
-            vertices = cv.boxPoints(boxes[i[0]])
+            vertices = cv.boxPoints(boxes[i])
             # scale the bounding box coordinates based on the respective ratios
             for j in range(4):
                 vertices[j][0] *= rW

samples/python/camera_calibration_show_extrinsics.py

@@ -1,5 +1,18 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
+
+'''
+Plot camera calibration extrinsics.
+
+usage:
+    camera_calibration_show_extrinsics.py [--calibration <input path>] [--cam_width] [--cam_height] [--scale_focal] [--patternCentric ]
+
+default values:
+    --calibration    : left_intrinsics.yml
+    --cam_width      : 0.064/2
+    --cam_height     : 0.048/2
+    --scale_focal    : 40
+    --patternCentric : True
+'''
 
 # Python 2/3 compatibility
 from __future__ import print_function

samples/python/common.py

@@ -222,7 +222,7 @@ def mosaic(w, imgs):
     pad = np.zeros_like(img0)
     imgs = it.chain([img0], imgs)
     rows = grouper(w, imgs, pad)
-    return np.vstack(map(np.hstack, rows))
+    return np.vstack(list(map(np.hstack, rows)))
 
 def getsize(img):
     h, w = img.shape[:2]

samples/python/digits.py

@@ -191,3 +191,4 @@ if __name__ == '__main__':
     model.save('digits_svm.dat')
 
     cv.waitKey(0)
+    cv.destroyAllWindows()

samples/python/digits_video.py

@@ -29,7 +29,7 @@ def main():
         src = sys.argv[1]
     except:
         src = 0
-    cap = video.create_capture(src)
+    cap = video.create_capture(src, fallback='synth:bg={}:noise=0.05'.format(cv.samples.findFile('sudoku.png')))
 
     classifier_fn = 'digits_svm.dat'
     if not os.path.exists(classifier_fn):

samples/python/facedetect.py

@@ -39,13 +39,13 @@ def main():
     except:
         video_src = 0
     args = dict(args)
-    cascade_fn = args.get('--cascade', "data/haarcascades/haarcascade_frontalface_alt.xml")
-    nested_fn  = args.get('--nested-cascade', "data/haarcascades/haarcascade_eye.xml")
+    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('samples/data/lena.jpg')))
+    cam = create_capture(video_src, fallback='synth:bg={}:noise=0.05'.format(cv.samples.findFile('lena.jpg')))
 
     while True:
         _ret, img = cam.read()

samples/python/qrcode.py

@@ -245,4 +245,6 @@ def main():
 
 
 if __name__ == '__main__':
+    print(__doc__)
     main()
+    cv.destroyAllWindows()

samples/python/stitching_detailed.py

@@ -246,9 +246,9 @@ def get_matcher(args):
     if matcher_type == "affine":
         matcher = cv.detail_AffineBestOf2NearestMatcher(False, try_cuda, match_conf)
     elif range_width == -1:
-        matcher = cv.detail.BestOf2NearestMatcher_create(try_cuda, match_conf)
+        matcher = cv.detail_BestOf2NearestMatcher(try_cuda, match_conf)
     else:
-        matcher = cv.detail.BestOf2NearestRangeMatcher_create(range_width, try_cuda, match_conf)
+        matcher = cv.detail_BestOf2NearestRangeMatcher(range_width, try_cuda, match_conf)
     return matcher
 
 

samples/python/text_skewness_correction.py

@@ -15,7 +15,7 @@ import argparse
 
 def main():
     parser = argparse.ArgumentParser()
-    parser.add_argument("-i", "--image", required=True, help="path to input image file")
+    parser.add_argument("-i", "--image", default="imageTextR.png", help="path to input image file")
     args = vars(parser.parse_args())
 
     # load the image from disk
@@ -37,9 +37,9 @@ def main():
     coords = cv.findNonZero(thresh)
     angle = cv.minAreaRect(coords)[-1]
     # the `cv.minAreaRect` function returns values in the
-    # range [-90, 0) if the angle is less than -45 we need to add 90 to it
-    if angle < -45:
-        angle = (90 + angle)
+    # range [0, 90) if the angle is more than 45 we need to subtract 90 from it
+    if angle > 45:
+        angle = (angle - 90)
 
     (h, w) = image.shape[:2]
     center = (w // 2, h // 2)
@@ -55,4 +55,6 @@ def main():
 
 
 if __name__ == "__main__":
+    print(__doc__)
     main()
+    cv.destroyAllWindows()

samples/python/tracker.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-
 '''
 Tracker demo
 
@@ -36,43 +35,49 @@ class App(object):
 
     def __init__(self, args):
         self.args = args
+        self.trackerAlgorithm = args.tracker_algo
+        self.tracker = self.createTracker()
 
-    def initializeTracker(self, image, trackerAlgorithm):
+    def createTracker(self):
+        if self.trackerAlgorithm == 'mil':
+            tracker = cv.TrackerMIL_create()
+        elif self.trackerAlgorithm == 'goturn':
+            params = cv.TrackerGOTURN_Params()
+            params.modelTxt = self.args.goturn
+            params.modelBin = self.args.goturn_model
+            tracker = cv.TrackerGOTURN_create(params)
+        elif self.trackerAlgorithm == 'dasiamrpn':
+            params = cv.TrackerDaSiamRPN_Params()
+            params.model = self.args.dasiamrpn_net
+            params.kernel_cls1 = self.args.dasiamrpn_kernel_cls1
+            params.kernel_r1 = self.args.dasiamrpn_kernel_r1
+            tracker = cv.TrackerDaSiamRPN_create(params)
+        else:
+            sys.exit("Tracker {} is not recognized. Please use one of three available: mil, goturn, dasiamrpn.".format(self.trackerAlgorithm))
+        return tracker
+
+    def initializeTracker(self, image):
         while True:
-            if trackerAlgorithm == 'mil':
-                tracker = cv.TrackerMIL_create()
-            elif trackerAlgorithm == 'goturn':
-                params = cv.TrackerGOTURN_Params()
-                params.modelTxt = self.args.goturn
-                params.modelBin = self.args.goturn_model
-                tracker = cv.TrackerGOTURN_create(params)
-            elif trackerAlgorithm == 'dasiamrpn':
-                params = cv.TrackerDaSiamRPN_Params()
-                params.model = self.args.dasiamrpn_net
-                params.kernel_cls1 = self.args.dasiamrpn_kernel_cls1
-                params.kernel_r1 = self.args.dasiamrpn_kernel_r1
-                tracker = cv.TrackerDaSiamRPN_create(params)
-            else:
-                sys.exit("Tracker {} is not recognized. Please use one of three available: mil, goturn, dasiamrpn.".format(trackerAlgorithm))
-
             print('==> Select object ROI for tracker ...')
             bbox = cv.selectROI('tracking', image)
             print('ROI: {}'.format(bbox))
+            if bbox[2] <= 0 or bbox[3] <= 0:
+                sys.exit("ROI selection cancelled. Exiting...")
 
             try:
-                tracker.init(image, bbox)
+                self.tracker.init(image, bbox)
             except Exception as e:
                 print('Unable to initialize tracker with requested bounding box. Is there any object?')
                 print(e)
                 print('Try again ...')
                 continue
 
-            return tracker
+            return
 
     def run(self):
         videoPath = self.args.input
-        trackerAlgorithm = self.args.tracker_algo
-        camera = create_capture(videoPath, presets['cube'])
+        print('Using video: {}'.format(videoPath))
+        camera = create_capture(cv.samples.findFileOrKeep(videoPath), presets['cube'])
         if not camera.isOpened():
             sys.exit("Can't open video stream: {}".format(videoPath))
 
@@ -82,7 +87,7 @@ class App(object):
         assert image is not None
 
         cv.namedWindow('tracking')
-        tracker = self.initializeTracker(image, trackerAlgorithm)
+        self.initializeTracker(image)
 
         print("==> Tracking is started. Press 'SPACE' to re-initialize tracker or 'ESC' for exit...")
 
@@ -92,7 +97,7 @@ class App(object):
                 print("Can't read frame")
                 break
 
-            ok, newbox = tracker.update(image)
+            ok, newbox = self.tracker.update(image)
             #print(ok, newbox)
 
             if ok:
@@ -101,7 +106,7 @@ class App(object):
             cv.imshow("tracking", image)
             k = cv.waitKey(1)
             if k == 32:  # SPACE
-                tracker = self.initializeTracker(image)
+                self.initializeTracker(image)
             if k == 27:  # ESC
                 break
 
@@ -112,22 +117,13 @@ 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 three available tracking algorithms: mil, goturn, dasiamrpn")
+    parser.add_argument("--tracker_algo", type=str, default="mil", help="One of available tracking algorithms: mil, goturn, dasiamrpn")
     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("--dasiamrpn_backend", type=int, default=0, help="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")
-    parser.add_argument("--dasiamrpn_target", type=int, default=0, help="Choose one of target computation devices:\
-                                                                         0: CPU target (by default),\
-                                                                         1: OpenCL,\
-                                                                         2: OpenCL fp16 (half-float precision),\
-                                                                         3: VPU")
+
     args = parser.parse_args()
     App(args).run()
     cv.destroyAllWindows()