我编写了以下代码,以便在OpenCV下检测python中的"一个或多个人脸的存在"。
import cv2
import sys
faceCascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cv2.namedWindow("preview")
vc = cv2.VideoCapture(0)
if vc.isOpened(): # try to get the first frame
rval, frame = vc.read()
else:
rval = False
while rval:
rval, frame = vc.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = faceCascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
frame = cv2.rectangle(frame,(x,y),(x+w,y+h),(255,0,0),2)
# Display the resulting frame
cv2.imshow('Preview', frame)
key = cv2.waitKey(20)
if key == 27: # exit on ESC
break
cv2.destroyWindow("preview")
cv2.destroyAllWindows()
我收到以下错误:
/usr/bin/python3.4 /home/yas/PycharmProjects/Ch10_OpenCV/Example.py
init done
opengl support available
OpenCV Error: Assertion failed (!empty()) in detectMultiScale, file /home/yas/opencv-3.0.0/modules/objdetect/src/cascadedetect.cpp, line 1634
Traceback (most recent call last):
File "/home/yas/PycharmProjects/Ch10_OpenCV/Example.py", line 32, in <module>
faces = faceCascade.detectMultiScale(gray, 1.3, 5)
cv2.error: /home/yas/opencv- 3.0.0/modules/objdetect/src/cascadedetect.cpp:1634: error: (-215) !empty() in function detectMultiScale
Process finished with exit code 1
因此,网络摄像头窗口不会打开,并且肯定没有检测到人脸。我在Linux Ubtunu下工作,使用Python解释器3.4.3。
这个错误是什么意思?如何解决?感谢分享您的意见
您必须在最后两行之前添加vc.release()
。它可能类似于:
vc.release()
cv2.destroyWindow("preview")
cv2.destroyAllWindows()