opencv 级联 hog 检测分类器显示为空

Question

我正在尝试传递 jpeg 图像以使用 hog 分类器检测人脸，但是我收到一个我不明白的错误。

非常感谢任何帮助。

我正在使用 python 3.7 并打开 cv 4.3.0

import cv2
import matplotlib.pyplot as plt

face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades +"hogcascade_pedestrians.xml")

def detect(gray, frame):  
    faces = face_cascade.detectMultiScale(gray, 1.3, 5) 
    for (x, y, w, h) in faces:
        cv2.rectangle(frame, (x, y), (x+w, y+h), (255, 0, 0), 2)
        roi_gray = gray[y:y+h, x:x+w] 
        roi_color = frame[y:y+h, x:x+w]
        
        eyes = eye_cascade.detectMultiScale(roi_gray, 1.1, 18)
        for (ex, ey, ew, eh) in eyes:
            cv2.rectangle(roi_color, (ex, ey), (ex+ew, ey+eh), (0, 255, 0), 2)
            
    return frame

frame = cv2.imread('./data/images/cctv_still.JPG')  
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) 
canvas = detect(gray, frame)
plt.imshow(canvas)
plt.show()

---------------------------------------------------------------------------
error                                     Traceback (most recent call last)
<ipython-input-40-26fd794bdcbb> in <module>
     19 frame = cv2.imread('./data/images/cctv_still.JPG')
     20 gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
---> 21 canvas = detect(gray, frame)
     22 plt.imshow(canvas)
     23 plt.show()

<ipython-input-40-26fd794bdcbb> in detect(gray, frame)
      5 
      6 def detect(gray, frame):
----> 7     faces = face_cascade.detectMultiScale(gray, 1.3, 5)
      8     for (x, y, w, h) in faces:
      9         cv2.rectangle(frame, (x, y), (x+w, y+h), (255, 0, 0), 2)

error: OpenCV(4.3.0) /io/opencv/modules/objdetect/src/cascadedetect.cpp:1689: error: (-215:Assertion failed) !empty() in function 'detectMultiScale'

Answer 1

自 opencv3.0 以来不再支持 hogcascades，因此它没有加载您的 yml。 （全身行人级联对于人脸检测也不可行）

请选择 haar 或 lbp 级联之一

（使用更新的 cv2（这里是 4.6.0-pre）你会得到一个信息更丰富The function/feature is not implemented) HOG cascade is not supported in 3.0 in function 'read' ）