我正在尝试将摄像机的帧流传输到flask api,并对其进行处理以检测所有帧中的面部并将其保存到磁盘。我的代码在这里,
def face(video_capture):
# Grab the list of names and the list of encodings
known_face_ids = list(all_face_encodings.keys())
known_face_encodings = np.array(list(all_face_encodings.values()))
while True:
process_this_frame = True
ret,frame = video_capture.read()
small_frame = cv2.resize(frame,(0,0),fx=0.25,fy=0.25)
rgb_small_frame = small_frame[:,:,::-1]
if process_this_frame:
face_locations = face_recognition.face_locations(rgb_small_frame)
face_encodings = face_recognition.face_encodings(rgb_small_frame,face_locations)
names_present = []
for face_encoding in face_encodings:
matches = face_recognition.compare_faces(known_face_encodings,face_encoding)
name = "Unknown"
if True in matches:
first_match_index = matches.index(True)
name = known_face_ids[first_match_index]
names_present.append(name)
process_this_frame = not process_this_frame
# Hit 'q' on the keyboard to quit!
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# Release handle to the webcam
video_capture.release()
cv2.destroyAllWindows()
return names_present
@app.route('/start_matching',methods=['POST'])
def attendance():
if request.method == 'POST':
if 'camera_id' not in request.args:
return 'Please provide the camera details'
camera_id = request.args.get('camera_id')
video_capture = cv2.VideoCapture(int(camera_id))
names_present = face(video_capture)
我正在尝试让前端具有开始和停止按钮。 “开始”应将上述api称为“开始匹配”。这样可以很好地工作并捕获流,将其拆分为帧,然后将编码与已知编码进行比较以找出其中存在的名称。但是,“停止”应停止将相机流式传输到上述api,并返回“ names_present”。
我尝试了另一个api调用
@app.route('/stop_matching',methods=['POST'])
def stop_attendance():
camera_id = request.args.get('camera_id')
video_capture = cv2.VideoCapture(int(camera_id))
video_capture.release()
return "Stopped the camera"
但是它不会停止相机并且不会返回“ names_present”列表。谁能指出我正确的方向?