Question

我正在从事一个计算机视觉项目，下面是我的代码应该如何工作：在 while 循环中，代码应该运行一个函数，该函数为前 5 帧返回一个字符串。如果该函数返回一个我正在寻找的输出，那么它应该继续运行其余的代码。剩下的代码涉及两个函数，主要执行人脸检测和识别任务。我希望这些任务仅以每秒 1 或 2 帧的速度执行。问题是我的代码没有执行检测和识别部分。

frame_id = 0
        while True:
            frame = video_capture.read()
            frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5)    #resize frame (optional)
            height, width = frame.shape[:2]
            frame_id += 1
            # Selecting 5 frames per second to
            
            flag = False
            if frame_id <= 5:
                event = Bodyevent(frame)
                if event is None:
                    continue
                if "1" in  event or "2" in event:
                    cv2.putText(frame, "DETECTED", (100, height - 20),
                                cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, 
                                (255, 255, 255), 1, cv2.LINE_AA)
                    flag = True
            
           
            if flag == True:
                # Now run the tasks 
                if frame_id % 6 == 0:
                    print("frame: ", frame_id)
                    # detect object #1
                    detect(frame)               
                    
                    find_results = []
                    
                    if frame.ndim == 2:
                        frame = facenet.to_rgb(frame)
                    frame = frame[:, :, 0:3]
                    bounding_boxes, _ = detect_face.detect_face(frame, minsize, pnet, rnet, onet, threshold, factor)
                    # detect number of faces and store in nrof_faces
                    nrof_faces = bounding_boxes.shape[0]
                    
                    
                    if nrof_faces > 0:
                        label = classify_face(frame)
                        # recognition task #
                    else:
                        print('Unable to align')

代码不执行人脸检测和识别任务

0 个答案: