openCV：在 Python 中使用 rtsp 访问 IP 摄像机时出错

如何解决openCV：在 Python 中使用 rtsp 访问 IP 摄像机时出错

进口

  let [isAuth,setIsAuth]=useState( false )

  return (
    <>
      {
       isAuth ? <Switch>
        <Route exact path={"/"} component={ Home } />

        <Route exact path={"/shopping-card"} component={ShoppingCard} />
        <Route exact path={"/order-success"} component={ OrderSuccess } />
        <Route exact path={"/orders"} component={ Orders } />
        <Route exact path={"/products"} component={ Products } />

        <Redirect to={"/user/login"} />
      </Switch> : <Switch>
        <Route exact path={"/user/signup"} component={ Signup } />
        <Route exact path={"/user/login"} component={ Login } />

        <Redirect to={"/user/login"} />
      </Switch>
      }
    </>
  )
}

export default Layout

程序变量和打印语句

import face_recognition
import os
import cv2
import pickle
import time
import smtplib
import dotenv

from datetime import date

加载已知的人脸编码

dotenv.load_dotenv()
KNOWN_FACES_DIR = 'known_faces'
FACES_DIR = "Faces"
# UNKNOWN_FACES_DIR = 'unknown_faces'
TOLERANCE = 0.7
FRAME_THICKNESS = 3
FONT_THICKNESS = 2
MODEL = 'cnn' 
print("Getting Video Feed...")
video_stream = cv2.VideoCapture(f"rtsp://{os.getenv('USERNAME')}: 
{os.getenv('PASSWORD_')}@{os.getenv('IP')}:{os.getenv('PORT')}/{os.getenv('NUM')}")
print("Video Feed Accessed...")

创建 ID

print('Loading known faces...')
known_faces = []
known_names = []


t = time.localtime()
system_time = time.strftime("%I:%M:%S",t)

try:
   os.mkdir(f"Logs/{str(date.today())}")
except FileExistsError:
    pass

for name in os.listdir(KNOWN_FACES_DIR):

# Next we load every file of faces of known person
for filename in os.listdir(f'{KNOWN_FACES_DIR}/{name}'):
    encoding = pickle.load(open(f'{KNOWN_FACES_DIR}/{name}/{filename}','rb'))
    known_faces.append(encoding)
    known_names.append(int(name))

寻找未知面孔

if len(known_names) > 0:
next_id = max(known_names) + 1

else:
next_id = 0

 counter = 0

这是我得到的错误

print('Processing unknown faces...')
while True:

ret,image = video_stream.read()
counter = counter + 1
locations = face_recognition.face_locations(image,model=MODEL)

encodings = face_recognition.face_encodings(image,locations)



print(f'found {len(encodings)} face(s)')
for face_encoding,face_location in zip(encodings,locations):

    # We use compare_faces (but might use face_distance as well)
    # Returns array of True/False values in order of passed known_faces
    results = face_recognition.compare_faces(known_faces,face_encoding,TOLERANCE)

    # Since order is being preserved,we check if any face was found then grab index
    # then label (name) of first matching known face withing a tolerance
    match = None
    if True in results:  # If at least one is true,get a name of first of found labels
        match = known_names[results.index(True)]
        print(f'Located ID {match} - {results}')
        pickle.dump(face_encoding,open(f"{KNOWN_FACES_DIR}/{match}/{match}-{system_time.replace(':','_')}.pkl",'wb'))
        server.sendmail(str(os.getenv('EMAIL')),str(os.getenv('TO')),f"ID {match} is at the front door")
        print("Sent Alert.")
        with open(f"Logs/{str(date.today())}/{str(date.today())}.log",'a') as f:
            f.write(f'Located ID {match}')
            f.write("\n")
            f.close()
        cv2.imwrite(f"Captures/ID_{match}_{str(date.today())}_{str(counter)}.png",image)
    else:
        match = str(next_id)
        next_id += 1
        known_names.append(match)
        known_faces.append(face_encoding)
        os.mkdir(f"{KNOWN_FACES_DIR}/{match}")
        pickle.dump(face_encoding,open(f"{KNOWN_FACES_DIR}/{match}/{match}-{int(time.time())}.pkl",'wb'))
    print("Sent Alert.")
        with open(f"Logs/{str(date.today())}/{str(date.today())}.log",'a') as f:
            f.write(f"New ID detected ID {match}")
            f.write("\n")
            f.close()
        cv2.imwrite(f"Captures/ID_{match}_{str(date.today())}_{str(counter)}",image)

cv2.imshow("Archer",image)

if cv2.waitKey(1) & 0xFF == ord('q'):
    break
cv2.waitKey(0)

您忘记Traceback (most recent call last): File "C:/Users/smith/Desktop/ArcherSurvalince/Montitor.py",line 79,in <module> locations = face_recognition.face_locations(image,model=MODEL) File "C:\Users\smith\Desktop\ArcherSurvalince\venv\lib\site-packages\face_recognition\api.py",line 119,in face_locations return [_trim_css_to_bounds(_rect_to_css(face.rect),img.shape) for face in _raw_face_locations(img,number_of_times_to_upsample,"cnn")] File "C:\Users\smith\Desktop\ArcherSurvalince\venv\lib\site-packages\face_recognition\api.py",line 103,in _raw_face_locations return cnn_face_detector(img,number_of_times_to_upsample) TypeError: __call__(): incompatible function arguments. The following argument types are supported: 1. (self: _dlib_pybind11.cnn_face_detection_model_v1,imgs: list,upsample_num_times: int=0,batch_size: int=128) -> std::vector<std::vector<dlib::mmod_rect,std::allocator<dlib::mmod_rect> >,std::allocator<std::vector<dlib::mmod_rect,std::allocator<dlib::mmod_rect> > > > 2. (self: _dlib_pybind11.cnn_face_detection_model_v1,img: array,upsample_num_times: int=0) -> std::vector<dlib::mmod_rect,std::allocator<dlib::mmod_rect> > Invoked with: <_dlib_pybind11.cnn_face_detection_model_v1 object at 0x0000026F4F29ADB0>,None,1 了吗？或者 ,, 等一些自动 转换是可选的，需要包含额外的标题 编译 pybind11 模块时。

我已经安装了 Pybind11，但我不知道如何修复它。

这似乎只发生在我尝试访问我的 IP 摄像头时 我可以很好地访问我的电脑摄像头，我拥有所有 安装的依赖项