import cv2 import sys import numpy as np import imutils as im IMG_SCALE_UP = 4 TEMPLATE_SEARCH_AREA = 0.5 (major_ver, minor_ver, subminor_ver) = cv2.__version__.split('.') print(cv2.__version__) def bbox_extend(bbox: cv2.typing.Rect, search_area: float): we2 = int(round(bbox[2]*search_area/2)) he2 = int(round(bbox[3]*search_area/2)) res = (int(round(bbox[0]-we2)),) res += (int(round(bbox[1]-he2)),) res += (int(bbox[2]+2*we2),) res += (int(bbox[3]+2*he2),) return res def image_crop(src, bbox: cv2.typing.Rect, search_area: float = 0): bbox = bbox_extend(bbox, search_area) x = bbox[0] y = bbox[1] w = bbox[2] h = bbox[3] dst = src[y:y+h, x:x+w] return dst def process_image_bbox(src): # convert to gray gray = cv2.cvtColor(src, cv2.COLOR_BGR2GRAY) return gray def match(source, template, angle, center): best_angle = 0 best_r = 0 best_max_loc = 0 im_source = im.resize(source, IMG_SCALE_UP * source.shape[0], IMG_SCALE_UP * source.shape[1]) for dangle in np.linspace(-1.0, +1.0, 10): # rotated and scale up to IMG_SCALE_UP-size im_template = im.rotate(template, angle + dangle, center=center, scale=IMG_SCALE_UP) # Perform template match operations res = cv2.matchTemplate(im_source, im_template, cv2.TM_CCOEFF_NORMED) (minVal, maxVal, minLoc, maxLoc) = cv2.minMaxLoc(res) r = maxVal if r > best_r: best_r = r best_angle = dangle best_max_loc = (maxLoc[0]/IMG_SCALE_UP, maxLoc[1]/IMG_SCALE_UP) angle += best_angle return angle, best_max_loc class Reference: def __init__(self, ref_gray): self.center = (0, 0) self.ref = cv2.cvtColor(ref_gray, cv2.COLOR_GRAY2BGR) self.work = self.ref.copy() cv2.namedWindow('Ref') cv2.setMouseCallback('Ref', self.extract_coordinates) def set(self): while True: cv2.imshow("Ref", self.work) key = cv2.waitKey(1) if key == 32: break elif key == 27: break return self.center def extract_coordinates(self, event, x, y, flags, parameters): if event == cv2.EVENT_LBUTTONDOWN: self.work = self.ref.copy() self.center = (x, y) print(f"Pixel at {self.center} = {self.work[y, x]}") self.work[y, x] = (0, 0, 255) print(f"Pixel at {self.center} = {self.work[y, x]}") trackers = { 'KCF': cv2.TrackerKCF, 'CSRT': cv2.TrackerCSRT, 'MIL': cv2.TrackerMIL, 'GOTURN': cv2.TrackerGOTURN, 'NANO': cv2.TrackerNano, 'MOSSE': cv2.legacy.TrackerMOSSE, 'TLD': cv2.legacy.TrackerTLD, 'BOOSTING': cv2.legacy.TrackerBoosting, 'MEDIANFLOW': cv2.legacy.TrackerMedianFlow } tracker_type = 'MOSSE' tracker = trackers[tracker_type].create() video = cv2.VideoCapture("./data/production_id 4525346 (1080p).mp4") # Exit if video not open # d. if not video.isOpened(): print("Could not open video") sys.exit() # Read first frame. ok, frame = video.read() if not ok: print('Cannot read video file') sys.exit() bbox = cv2.selectROI("Frame", frame, False) image_template = process_image_bbox(image_crop(frame, bbox, TEMPLATE_SEARCH_AREA)) ref = Reference(image_template) ref_center = ref.set() print(f"ref_center = {ref_center}") # Initialize tracker with first frame and bounding box tracker.create() tracker.init(frame, bbox) current_angle = 0 while True: # Read a new frame ok, frame = video.read() if not ok: break # Start timer timer = cv2.getTickCount() # Update tracker ok, bbox = tracker.update(frame) image_bbox = process_image_bbox(image_crop(frame, bbox)) image_template_rotated = image_template if ok: current_angle, max_loc = match(image_bbox, image_template, current_angle, ref_center) # determine the starting and ending (x, y)-coordinates of the # bounding box (startX, startY) = max_loc print(f"startX: {startX}, startY: {startY}") image_template_rotated = im.rotate(image_template, current_angle, center=ref_center) # draw the bounding box on the image p1 = (int(startX + bbox[0]), int(startY + bbox[1])) p2 = (int(bbox[0]+bbox[2]), int(bbox[1]+bbox[3])) cv2.rectangle(frame, p1, p2, (255, 0, 0), 3) # Calculate Frames per second (FPS) fps = cv2.getTickFrequency() / (cv2.getTickCount() - timer) else: # Tracking failure cv2.putText(frame, "Tracking failure detected", (100, 80), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 255), 2) # Display tracker type on frame cv2.putText(frame, tracker_type + " Tracker", (100, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50, 170, 50), 2) # Display FPS on frame cv2.putText(frame, "FPS : " + str(int(fps)), (100, 50), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (50, 170, 50), 2) # Display result cv2.imshow("Tracking", frame) cv2.imshow("image_bbox", image_template_rotated) # Exit if ESC pressed k = cv2.waitKey(1) & 0xff if k == 27: break