方法一：目標(biāo)物體白色，其余黑色

import cv2 import numpy as npdef extrace_object():capture = cv2.VideoCapture("G:/Juptyer_workspace/study/data/yy.mp4")while(True):ret,frame = capture.read()if ret==False:breakhsv = cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)lower = np.array([78,43,46])#由于水杯是青色的故需要根據(jù)表格選出hsv對(duì)應(yīng)的min值upper = np.array([99,255,255])#由于水杯是青色的故需要根據(jù)表格選出hsv對(duì)應(yīng)的max值mask = cv2.inRange(hsv,lowerb=lower,upperb=upper)cv2.imshow("video",frame)cv2.imshow("mask",mask)c = cv2.waitKey(40)if c==27:breakt1 = cv2.getTickCount() extrace_object() t2 = cv2.getTickCount() time = (t2-t1)/cv2.getTickFrequency()#顯示當(dāng)前運(yùn)行時(shí)間 print("time:%s ms"%(time*1000))#輸出當(dāng)前運(yùn)行時(shí)間單位為ms cv2.waitKey(0)cv2.destroyAllWindows()

效果圖如下：

方法二：目標(biāo)物體顏色保留，其余黑色

import cv2 import numpy as npdef extrace_object():capture = cv2.VideoCapture("G:/Juptyer_workspace/study/data/yy.mp4")while(True):ret,frame = capture.read()if ret==False:breakhsv = cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)lower = np.array([78,43,46])#由于水杯是青色的故需要根據(jù)表格選出hsv對(duì)應(yīng)的min值upper = np.array([99,255,255])#由于水杯是青色的故需要根據(jù)表格選出hsv對(duì)應(yīng)的max值mask = cv2.inRange(hsv,lowerb=lower,upperb=upper)dst = cv2.bitwise_and(frame,frame,mask=mask)cv2.imshow("video",frame)#cv2.imshow("mask",mask)cv2.imshow("dst",dst)c = cv2.waitKey(40)if c==27:breakt1 = cv2.getTickCount() extrace_object() t2 = cv2.getTickCount() time = (t2-t1)/cv2.getTickFrequency()#顯示當(dāng)前運(yùn)行時(shí)間 print("time:%s ms"%(time*1000))#輸出當(dāng)前運(yùn)行時(shí)間單位為ms cv2.waitKey(0)cv2.destroyAllWindows()

效果圖如下：

cv2.inRange(hsv,lowerb=lower,upperb=upper)：對(duì)HSV顏色過(guò)濾，lowerb和upperb需要查下面的表進(jìn)行顏色轉(zhuǎn)換

BGR和HSV對(duì)應(yīng)色彩表

創(chuàng)作挑戰(zhàn)賽新人創(chuàng)作獎(jiǎng)勵(lì)來(lái)咯，堅(jiān)持創(chuàng)作打卡瓜分現(xiàn)金大獎(jiǎng)

總結(jié)

以上是生活随笔為你收集整理的对视频中的特征颜色物体(青色水杯)进行跟踪的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。