具有多处理功能的 MediaPipe 姿态估计器挂在其处理函数上

Question

我目前正在尝试使用 Python 的多处理库将 MediaPipe 姿势估计器实现为基于事件的独立进程，但它挂在 MediaPipe 的 Pose.process() 函数上。

我用另一个进程（readFrames）输入帧。每当捕获帧时，它都会写入共享对象并告诉 MediaPipe 进程 (MediaPipeRunner) 开始处理当前图像：

def readFrames(ns, event):
  #initialize the video capture object
  cap = cv2.VideoCapture(0)
  while cap.isOpened():
    ret, frame = cap.read()
    if ret:
        ns.frame = frame
        event.set()
        cv2.imshow('Orijinal Frame', frame)
        if cv2.waitKey(1) & 0xFF == ord('q'):
            cap.release()
            cv2.destroyAllWindows()
            return -1
    else:
        return


class MediaPipeRunner(mproc.Process):

    def __init__(self, name, nsFrame, nsMediaPipe, eventWait, eventPublish):
        super(MediaPipeRunner, self).__init__()
        
        # Specify a name for the instance
        self.name = name
        
        # Input and output namespaces
        self.nsFrame = nsFrame
        self.nsMediaPipe = nsMediaPipe

        # Waiter and publisher events
        self.eventWait = eventWait
        self.eventPublish = eventPublish

        # Create a pose estimator from MediaPipe
        mp_pose = mp.solutions.pose

        # Specify pose estimator parameters (static)
        static_image_mode = True
        model_complexity = 1
        enable_segmentation = True  # DONT CHANGE
        min_detection_confidence = 0.5

        # Create a pose estimator here
        self.pose = mp_pose.Pose(
        static_image_mode=static_image_mode,
        model_complexity=model_complexity,
        enable_segmentation=enable_segmentation,
        min_detection_confidence=min_detection_confidence,
        smooth_landmarks=False,
        )

    def run(self):
        while True:
            eventFrame.wait()
            
            # This part is where it gets stuck:
            results = self.pose.process(cv2.cvtColor(self.nsFrame.frame, cv2.COLOR_BGR2RGB))

            if not results.pose_landmarks:
                continue

            self.nsMediaPipe.segmentation = results.segmentation_mask
            eventMP.set()

这是我绑定进程、命名空间和事件的方式：

if __name__=="__main__":

    mgr = mproc.Manager()

    nsFrame = mgr.Namespace()
    nsMP = mgr.Namespace()

    eventFrame = mproc.Event()
    eventMP = mproc.Event()

    camCap = mproc.Process(name='camCap', target=readFrames, args=(nsFrame, eventFrame, ))
    camCap.daemon=True

    mpCap = MediaPipeRunner('mpCap', nsFrame, nsMP, eventFrame, eventMP, )
    mpCap.daemon=True

    camCap.start()
    mpCap.start()

    camCap.join()
    mpCap.join()

我是不是在进程上采取了错误的步骤，或者 MediaPipe 与 Python 的多处理库不兼容？

任何帮助将不胜感激，提前致谢:)

P.S.: 我通过 pip 安装了 MediaPipe 并且版本 0.8.9.1 存在。

Answer 1

我发现了问题：process 函数在 Python 中使用 with 结构时正确运行（我知道为什么）：

    with mp_pose.Pose(
        static_image_mode=static_image_mode,
        model_complexity=model_complexity,
        enable_segmentation=enable_segmentation,
        min_detection_confidence=min_detection_confidence,
        smooth_landmarks=False,
        ) as pose:

现在这部分有效了！

    results = self.pose.process(cv2.cvtColor(self.nsFrame.frame, cv2.COLOR_BGR2RGB))

希望对您有所帮助。

具有多处理功能的 MediaPipe 姿态估计器挂在其处理函数上

MediaPipe pose estimator with multiprocessing hangs on its process function

python

events

multiprocessing

python-multiprocessing

mediapipe