Python OpenCV-基于特定对象条件保存视频时，并非所有这样的帧都被保存

我在Python中使用opencv，并试图在帧中出现特定类型的对象/标签（例如“伞”）时仅录制/保存视频中的帧

问题：

def vid_objects_detection(type=0, confidence_threshold=0.5, image_quality=416):

    classes = []

    # reading category names from coco text file and inserting in classes list
    with open("coco.names", "r") as f:
        classes = [line.strip() for line in f.readlines()]

    net = cv2.dnn.readNet("yolov3-tiny.weights", "yolov3-tiny.cfg") # using tiny versions of weights & config file

    layer_names = net.getLayerNames()    
    output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]

    # Loading video
    cap = cv2.VideoCapture(type)  # use 0 for webcam   

    _, frame = cap.read()
    height, width, channels = frame.shape

    # providing codec for writing frames to video 
    fourcc = cv2.VideoWriter_fourcc(*'MP4V')

    # Write video with name & size. Should be of same size(width, height) as original video
    out_vid = cv2.VideoWriter('obj_detect4_'+str(type), fourcc, 20.0, (width,height))

    font = cv2.FONT_HERSHEY_COMPLEX_SMALL 
    starting_time = time.time()
    frame_id = 0

    while True:
        _, frame = cap.read()

        frame_id +=1

        total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
        height, width, channels = frame.shape       

        blob = cv2.dnn.blobFromImage(frame, 0.00392, (image_quality, image_quality), (0, 0, 0), True, crop=False)
        net.setInput(blob)

        outs = net.forward(output_layers)

        # For showing informations on screen
        class_ids = []
        confidences = []
        boxes = []
        for out in outs:
            for detection in out:
                # claculated scores, class_id, confidence                   

                if confidence > confidence_threshold:                      
                    # claculatedd center_x, center_y, w,h,x,y
                    boxes.append([x, y, w, h])
                    confidences.append(float(confidence))
                    class_ids.append(class_id)
                    print("confidences:", confidences)
                    print(class_ids)
                    print("boxes", boxes)

        indexes = cv2.dnn.NMSBoxes(boxes, confidences, confidence_threshold, 0.4)

        for i in range(len(boxes)):
            if i in indexes:
                x, y, w, h = boxes[i]
                label = str(classes[class_ids[i]])

        elapsed_time = time.time() - starting_time
        fps = frame_id / elapsed_time
        time_display = time.strftime("%a, %d%b%Y %H:%M:%S", time.localtime())
        cv2.putText(frame,"|FPS: " + str(round(fps,3)), (10, 40), font, 1, (0,255,0), 1)
        print(fps)

        # saving video frame by frame 
    if i == '':
        pass
    else:
        if 'umbrella' in label:
            out_vid.write(frame)

        key = cv2.waitKey(5)
        if key == 27: 
            break

    cap.release()
    out_vid.release()
    cv2.destroyAllWindows()

# calling function
vid_objects_detection("walking.mp4")

它正确地从第一次在帧中找到提到的对象/标签的实例开始保存帧，但如果该对象/标签在接下来的几帧中不存在，并且仅在几帧之后出现，则这些帧不会保存到我正在保存它的mp4文件中

它只保存具有所述对象的第一个连续帧，不保存后续帧

阅读了此链接中的建议后，我将框架编写步骤放在for循环中编辑了代码，如下所示：

框写我尝试即兴创作的一段代码

# saving video frame by frame             
for frame_numb in range(total_frames):                
    if i == '':
        pass
    else:
        if "umbrella" in label:
            print("umbrella in labels")

            # Issue causing part where I may need some change
            out_vid.write(frame[frame_numb])

上述代码更改的结果：

def vid_objects_detection(type=0, confidence_threshold=0.5, image_quality=416):

    classes = []

    # reading category names from coco text file and inserting in classes list
    with open("coco.names", "r") as f:
        classes = [line.strip() for line in f.readlines()]

    net = cv2.dnn.readNet("yolov3-tiny.weights", "yolov3-tiny.cfg") # using tiny versions of weights & config file

    layer_names = net.getLayerNames()    
    output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]

    # Loading video
    cap = cv2.VideoCapture(type)  # use 0 for webcam   

    _, frame = cap.read()
    height, width, channels = frame.shape

    # providing codec for writing frames to video 
    fourcc = cv2.VideoWriter_fourcc(*'MP4V')

    # Write video with name & size. Should be of same size(width, height) as original video
    out_vid = cv2.VideoWriter('obj_detect4_'+str(type), fourcc, 20.0, (width,height))

    font = cv2.FONT_HERSHEY_COMPLEX_SMALL 
    starting_time = time.time()
    frame_id = 0

    while True:
        _, frame = cap.read()

        frame_id +=1

        total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
        height, width, channels = frame.shape       

        blob = cv2.dnn.blobFromImage(frame, 0.00392, (image_quality, image_quality), (0, 0, 0), True, crop=False)
        net.setInput(blob)

        outs = net.forward(output_layers)

        # For showing informations on screen
        class_ids = []
        confidences = []
        boxes = []
        for out in outs:
            for detection in out:
                # claculated scores, class_id, confidence                   

                if confidence > confidence_threshold:                      
                    # claculatedd center_x, center_y, w,h,x,y
                    boxes.append([x, y, w, h])
                    confidences.append(float(confidence))
                    class_ids.append(class_id)
                    print("confidences:", confidences)
                    print(class_ids)
                    print("boxes", boxes)

        indexes = cv2.dnn.NMSBoxes(boxes, confidences, confidence_threshold, 0.4)

        for i in range(len(boxes)):
            if i in indexes:
                x, y, w, h = boxes[i]
                label = str(classes[class_ids[i]])

        elapsed_time = time.time() - starting_time
        fps = frame_id / elapsed_time
        time_display = time.strftime("%a, %d%b%Y %H:%M:%S", time.localtime())
        cv2.putText(frame,"|FPS: " + str(round(fps,3)), (10, 40), font, 1, (0,255,0), 1)
        print(fps)

        # saving video frame by frame 
    if i == '':
        pass
    else:
        if 'umbrella' in label:
            out_vid.write(frame)

        key = cv2.waitKey(5)
        if key == 27: 
            break

    cap.release()
    out_vid.release()
    cv2.destroyAllWindows()

# calling function
vid_objects_detection("walking.mp4")

它只创建256kb的文件，文件无法打开/无法写入任何内容

如果我在代码中做了以下更改，那么它只保存满足该条件的视频的第一帧，并在整个时间内运行相同的帧

    # saving video frame by frame             
    for frame_numb in range(total_frames):                
        if i == '':
            pass
        else:
            if "umbrella" in label:
                print("umbrella in labels")

                # Issue causing part where I may need some change
                out_vid.write(frame)

共享下面更大的代码块以供参考：

def vid_objects_detection(type=0, confidence_threshold=0.5, image_quality=416):

    classes = []

    # reading category names from coco text file and inserting in classes list
    with open("coco.names", "r") as f:
        classes = [line.strip() for line in f.readlines()]

    net = cv2.dnn.readNet("yolov3-tiny.weights", "yolov3-tiny.cfg") # using tiny versions of weights & config file

    layer_names = net.getLayerNames()    
    output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]

    # Loading video
    cap = cv2.VideoCapture(type)  # use 0 for webcam   

    _, frame = cap.read()
    height, width, channels = frame.shape

    # providing codec for writing frames to video 
    fourcc = cv2.VideoWriter_fourcc(*'MP4V')

    # Write video with name & size. Should be of same size(width, height) as original video
    out_vid = cv2.VideoWriter('obj_detect4_'+str(type), fourcc, 20.0, (width,height))

    font = cv2.FONT_HERSHEY_COMPLEX_SMALL 
    starting_time = time.time()
    frame_id = 0

    while True:
        _, frame = cap.read()

        frame_id +=1

        total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
        height, width, channels = frame.shape       

        blob = cv2.dnn.blobFromImage(frame, 0.00392, (image_quality, image_quality), (0, 0, 0), True, crop=False)
        net.setInput(blob)

        outs = net.forward(output_layers)

        # For showing informations on screen
        class_ids = []
        confidences = []
        boxes = []
        for out in outs:
            for detection in out:
                # claculated scores, class_id, confidence                   

                if confidence > confidence_threshold:                      
                    # claculatedd center_x, center_y, w,h,x,y
                    boxes.append([x, y, w, h])
                    confidences.append(float(confidence))
                    class_ids.append(class_id)
                    print("confidences:", confidences)
                    print(class_ids)
                    print("boxes", boxes)

        indexes = cv2.dnn.NMSBoxes(boxes, confidences, confidence_threshold, 0.4)

        for i in range(len(boxes)):
            if i in indexes:
                x, y, w, h = boxes[i]
                label = str(classes[class_ids[i]])

        elapsed_time = time.time() - starting_time
        fps = frame_id / elapsed_time
        time_display = time.strftime("%a, %d%b%Y %H:%M:%S", time.localtime())
        cv2.putText(frame,"|FPS: " + str(round(fps,3)), (10, 40), font, 1, (0,255,0), 1)
        print(fps)

        # saving video frame by frame 
    if i == '':
        pass
    else:
        if 'umbrella' in label:
            out_vid.write(frame)

        key = cv2.waitKey(5)
        if key == 27: 
            break

    cap.release()
    out_vid.release()
    cv2.destroyAllWindows()

# calling function
vid_objects_detection("walking.mp4")

---

我在代码中删减了一些小的计算并插入了注释，以减少代码的长度

有时视频编解码器会执行所谓的关键帧压缩。这意味着，一个帧被完全存储，比如每10帧存储一次，中间的所有其他帧被存储为更改或增量。在这种情况下，当您尝试仅在帧之间保存这些时，它们可能无法保存。但是，在这些情况下，如果按顺序迭代每个帧，则保存帧是有效的

---

可能你可以注释掉line out\u vid=

cv2。VideoWriter（'obj\u detect4\u'+str（type），fourcc，20.0，（宽度，高度））

，然后根据你的情况尝试保存网络摄像头流中的帧。

有时视频编解码器会执行所谓的关键帧压缩。这意味着，一个帧被完全存储，比如每10帧存储一次，中间的所有其他帧被存储为更改或增量。在这种情况下，当您尝试仅在帧之间保存这些时，它们可能无法保存。但是，在这些情况下，如果按顺序迭代每个帧，则保存帧是有效的

---

可能您可以注释掉line out\u vid=

cv2.VideoWriter（'obj\u detect4\u'+str（type），fourcc，20.0，（宽度，高度））

，然后根据您的条件尝试保存网络摄像头流中的帧。

您设置了if条件out for循环@因为我是蝙蝠侠谢谢你的建议。实际上，“标签”被帧中出现的最后一个对象/标签覆盖。所以它很难捕捉到“伞”的框架。所以我创建了一个列表，开始在其中插入标签名，并在if条件下使用该列表，而不仅仅是标签，即使不使用for循环，它也可以正常工作。@ViSa您可以共享更新的代码吗？我正在做一个类似的项目，谢谢你设置了if条件out for循环@因为我是蝙蝠侠谢谢你的建议。实际上，“标签”被帧中出现的最后一个对象/标签覆盖。所以它很难捕捉到“伞”的框架。所以我创建了一个列表，开始在其中插入标签名，并在if条件下使用该列表，而不仅仅是标签，即使不使用for循环，它也可以正常工作。@ViSa您可以共享更新的代码吗？我正在做一个类似的项目，谢谢Hanks提供的信息。我肯定会尝试你的建议，但现在我已经做到了。问题是，每个帧中的标签都被该帧的最后一个标签覆盖。所以大多数时候我搜索的标签都不能作为帧中的最后一个标签使用。所以我创建了一个列表来保存框架中出现的所有标签，并在列表中进行匹配。但是你给了我一个很好的建议，我一定会尝试的。谢谢你提供的信息。我肯定会尝试你的建议，但现在我已经做到了。问题是，每个帧中的标签都被该帧的最后一个标签覆盖。所以大多数时候我搜索的标签都不能作为帧中的最后一个标签使用。所以我创建了一个列表来保存框架中出现的所有标签，并在列表中进行匹配。但是你给了我一个很好的建议，我一定会尝试的。