0

我的主要想法是在视频的每一帧上实现姿势估计，但是每当我运行我的代码时，它都会显示下面给出的错误。我从这里引用了我的代码https://github.com/spmallick/learnopencv/blob/master/OpenPose/OpenPoseVideo.py

有人可以帮忙吗？

<ipython-input-29-64ed315d8f5a> in <module>
     37                               (0, 0, 0), swapRB=False, crop=False)
     38     net.setInput(inpBlob)
---> 39     output = net.forward()
     40 
     41     H = output.shape[2]

error: OpenCV(4.5.5) /Users/runner/work/opencv-python/opencv-python/opencv/modules/core/src/matrix.cpp:1242: error: (-209:Sizes of input arguments do not match) Requested and source matrices have different count of elements in function 'reshape'.

这是我的代码。

import cv2
import time
import numpy as np


protoFile = "pose_deploy_linevec.prototxt"
weightsFile = "pose_iter_440000.caffemodel"
nPoints = 18
POSE_PAIRS = [ [1,0],[1,2],[1,5],[2,3],[3,4],[5,6],[6,7],[1,8],[8,9],[9,10],[1,11],[11,12],[12,13],[0,14],[0,15],[14,16],[15,17]]


inWidth = 368
inHeight = 368
threshold = 0.1


input_source = "animations/lifting/ali_lift.mp4"
cap = cv2.VideoCapture(input_source)
hasFrame, frame = cap.read()

vid_writer = cv2.VideoWriter('output.avi',cv2.VideoWriter_fourcc('M','J','P','G'), 10, (frame.shape[1],frame.shape[0]))


while cv2.waitKey(1) < 0:
    t = time.time()
    hasFrame, frame = cap.read()
    frameCopy = np.copy(frame)
    if not hasFrame:
        cv2.waitKey()
        break
  
    frameWidth = frame.shape[1]
    frameHeight = frame.shape[0]

    inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight),
                              (0, 0, 0), swapRB=False, crop=False)
    net.setInput(inpBlob)
    output = net.forward()

    H = output.shape[2]
    W = output.shape[3]
    # Empty list to store the detected keypoints
    points = []

    for i in range(nPoints):
        # confidence map of corresponding body's part.
        probMap = output[0, i, :, :]

        # Find global maxima of the probMap.
        minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)
        
        # Scale the point to fit on the original image
        x = (frameWidth * point[0]) / W
        y = (frameHeight * point[1]) / H

        if prob > threshold : 
            cv2.circle(frameCopy, (int(x), int(y)), 8, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)
            cv2.putText(frameCopy, "{}".format(i), (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2, lineType=cv2.LINE_AA)

            # Add the point to the list if the probability is greater than the threshold
            points.append((int(x), int(y)))
        else :
            points.append(None)

    # Draw Skeleton
    for pair in POSE_PAIRS:
        partA = pair[0]
        partB = pair[1]

        if points[partA] and points[partB]:
            cv2.line(frame, points[partA], points[partB], (0, 255, 255), 3, lineType=cv2.LINE_AA)
            cv2.circle(frame, points[partA], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)
            cv2.circle(frame, points[partB], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)

    cv2.putText(frame, "time taken = {:.2f} sec".format(time.time() - t), (50, 50), cv2.FONT_HERSHEY_COMPLEX, .8, (255, 50, 0), 2, lineType=cv2.LINE_AA)
    # cv2.putText(frame, "OpenPose using OpenCV", (50, 50), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 50, 0), 2, lineType=cv2.LINE_AA)
    # cv2.imshow('Output-Keypoints', frameCopy)
    cv2.imshow('Output-Skeleton', frame)

    vid_writer.write(frame)

vid_writer.release()

我是姿势估计的新手，所以我很难理解我错在哪里。

4

0 回答 0