Here is the code for my live camera in opencv.
cap = cv2.VideoCapture(0)
while(True):
ret, frame = cap.read()
# Our operations on the frame come here
# Display the resulting frame
cv2.rectangle(frame, (0,0,int(frame.shape[0]/3),frame.shape[1]),(255,0,0),2)
cv2.rectangle(frame, (int(frame.shape[0]),0,int(frame.shape[0]*(1/3)),frame.shape[1]),(0,0,255),2)
#
# leftPortion = frame[:,0:int(frame.shape[0]/3),:]
# rightPortion = frame[:,int(frame.shape[0]*(3/3)):,:]
# BOXES = detect_hands(frame,graph,sess)
# boxes = predict(BOXES,frame.shape[0],frame.shape[1])
#
# x_min, x_max, y_min, y_max = boxes[0]
# x = int((x_min + x_max) / 2)
# y = int((y_min + y_max) / 2)
# cv2.circle(frame, (x, y), 5, (255,0,0), -1)
# if len(boxes) == 1:
# x_min, x_max, y_min, y_max = boxes[0]
# x = int((x_min + x_max) / 2)
# y = int((y_min + y_max) / 2)
# cv2.circle(frame, (x, y), 20, (255,0,0), -1)
cv2.imshow('window',frame)
if cv2.waitKey(1)==ord('q'):
break
# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()
The problem is, it runs good. Quite good, but after certain time, (not exactly the same every time), the camera crashes with the exit code -1073741819 (0xC0000005). No errors, nothing. I don't even remember tweaking any settings, apart from one regedit setting when camera was failed to be detected by the laptop, but later I reverted whatever I did. Any solution for this problem please?
if you are running it on the Raspberry Pi, it crashes when the memory is full and you have to reload it in order to bypass this error
User contributions licensed under CC BY-SA 3.0