opencvcv2在我的代码中检测运动的问题

如何解决opencvcv2在我的代码中检测运动的问题

我已经编写了一个代码来检测网络摄像头的运动，但是每当我启动该代码时，它都可以工作，但是它可以检测整个全屏屏幕，而不是屏幕上移动的对象。我注意到，如果关闭相机，似乎会删除检测到的东西。这是代码：

import cv2

first_frame = None

video = cv2.VideoCapture(0)

while True:
    check,frame = video.read()

    gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
    gray = cv2.GaussianBlur(gray,(21,21),0)

    if first_frame is None:
        first_frame=gray
        continue

    delta_frame = cv2.absdiff(first_frame,gray)
    thresh_frame = cv2.threshold(delta_frame,30,255,cv2.THRESH_BINARY)[1]
    thresh_frame = cv2.dilate(thresh_frame,None,iterations=2)

    (cnts,_) = cv2.findContours(thresh_frame.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

    for contour in cnts:
        if cv2.contourArea(contour) < 4000:
            continue

        (x,y,w,h)= cv2.boundingRect(contour)
        cv2.rectangle(frame,(x,y),(x + w,y + h),(0,225,0),3)


    cv2.imshow("Delta Frame",delta_frame)
    cv2.imshow("Capturing",gray)
    cv2.imshow("Threshold Frame",thresh_frame)
    cv2.imshow("Color Frame",frame)

    key = cv2.waitKey(5)

    if key==ord('q'):
        break

video.release()
cv2.destroyAllWindows()

该代码应该只能检测屏幕中的移动物体。

解决方法

刚开始使用opencv时，我也遇到过类似的问题；该程序的问题是第一帧，第一帧捕获了黑屏。第一帧（first_frame）和下一帧（灰色）的cv2.absdiff检测到的差异足够大，以致在整个屏幕上都显示了cv2.findContours。这可能是由于相机延迟造成的

可以通过在相机加载到程序录制带有time.sleep（）的第一帧（first_frame）之间的时间间隔稍加延迟来解决。试试这个：

import cv2,time


first_frame = None

video = cv2.VideoCapture(0)
# the camera has some lag time hence the starting of video.read outside loop and sleep
video.read()
time.sleep(2)

while True:
    check,frame = video.read()

    gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
    gray = cv2.GaussianBlur(gray,(21,21),0)

    if first_frame is None:
        first_frame=gray
        continue

    delta_frame = cv2.absdiff(first_frame,gray)
    thresh_frame = cv2.threshold(delta_frame,30,255,cv2.THRESH_BINARY)[1]
    thresh_frame = cv2.dilate(thresh_frame,None,iterations=2)

    (cnts,_) = cv2.findContours(thresh_frame.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

    for contour in cnts:
        if cv2.contourArea(contour) < 4000:
            continue

        (x,y,w,h)= cv2.boundingRect(contour)
        cv2.rectangle(frame,(x,y),(x + w,y + h),(0,225,0),3)


    cv2.imshow("Delta Frame",delta_frame)
    cv2.imshow("Capturing",gray)
    cv2.imshow("Threshold Frame",thresh_frame)
    cv2.imshow("Color Frame",frame)

    key = cv2.waitKey(5)

    if key==ord('q'):
        break

video.release()
cv2.destroyAllWindows()

time.sleep负责相机启动的延迟时间。 试试代码，它在这里起作用