Raspberry Pi 相机和 Python 脚本在检测对象崩溃时崩溃

Question

我写了一段代码来检测我家发生的任何类型的入侵，如果检测到任何类型的对象，就会形成边界框，然后需要执行进一步的操作。当我在我的设备的摄像头（笔记本电脑摄像头）上测试代码时，它工作正常。但是当我运行 Raspberry Pi 3B 上带有摄像头模块（非 USB 摄像头）的同一段代码时，它崩溃并且脚本停止执行。

我在此处附上代码片段

import cv2 
import numpy as np
cv2.namedWindow("Preview")
cam = cv2.VideoCapture(0)

while cam.isOpened():
    ret, frame1 = cam.read()
    ret, frame2 = cam.read()

    diff = cv2.absdiff(frame1,frame2)

    grey = cv2.cvtColor(diff, cv2.COLOR_BGR2GRAY)

    blur = cv2.GaussianBlur(grey, (5, 5), 0)

    _, thresh = cv2.threshold(blur, 20, 255,cv2.THRESH_BINARY)

    dilated = cv2.dilate(thresh, None, iterations=3)

    contours, _ = cv2.findContours(dilated, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

    for c in contours:
        if cv2.contourArea(c) >= 10000:
           
            x,y,w,h = cv2.boundingRect(frame1)
            cv2.rectangle(frame1,(x,y),(x+w,y+h), (0,255,0),3)
        else:
            continue
    
    if not ret:
        break

    cv2.imshow("Preview", frame1)

    if cv2.waitKey(10)==ord('q'):
        break


cam.release()
cv2.destroyAllWindows()

我收到的错误消息是

x,y,w,h = cv2.boundingRect(frame1)
cv2.error: OpenCV(4.4.0) /tmp/pip-wheel-ggn8r4df/opencv-contrib-python_52a54d5431f647899265a8f5082f7e73/opencv/modules/imgproc/src/shapedescr.cpp:1044: error: (-215:Assertion failed) img.depth() <= CV_8S && img.channels() == 1 in function 'maskBoundingRect'

Answer 1

感谢@toyata Supra。错误已解决，程序按预期执行。

解决方案：

x,y,w,h = cv2.boundingRect(c)

Raspberry Pi 相机和 Python 脚本在检测对象崩溃时崩溃

Raspberry Pi Camera and Python Script Crashes while detecting Objects Crashes

python

opencv

object-detection

raspberry-pi

raspberry-pi3