两个边界框接触时如何保存图像

Question

两个盒子相互接触时如何保存图像，我希望当边界框面接触香烟边界框时，图像将作为一个整体保存。

这是代码：

import cv2
import numpy as np
cigarette = cv2.CascadeClassifier('classifier/cigarette-cascade.xml')
faced = cv2.CascadeClassifier('classifier/face-detect.xml')

cam = cv2.VideoCapture(0)
while True:
    ret, img = cam.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = faced.detectMultiScale(gray, 1.3, 5)
    cigarettes = cigarette.detectMultiScale(gray, 1.3, 5)
    for x,y,w,h in faces:
        cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
    for (x, y, w, h) in cigarettes:
        cv2.rectangle(img, (x, y), (x + w, y + h), (255, 255, 0), 2)
    cv2.imshow('test', img)
    k = cv2.waitKey(1) & 0xff
    if k == 27:
        break
cv2.destroyAllWindows()

Answer 1

您可以检查点坐标是否在另一个框中：

cnt=0
for x,y,w,h in faces:
    for x_,y_,w_,h_ in cigarettes:
        if not len(set(range(x,x+w))&set(range(x_,x_+w_)))==0 and \
            not len(set(range(y,y+h))&set(range(y_,y_+h_)))==0:
            cnt +=1
            cv2.imwrite("save_%s.jpg"%cnt, img)