檢測有沒有物體移動

import cv2 import timecamera = cv2.VideoCapture(0) if camera is None:print('請先連接攝像頭')exit()fps = 5 # 幀率 pre_frame = None # 總是取前一幀做為背景（不用考慮環境影響） play_music = Falsewhile True:start = time.time()res, cur_frame = camera.read()if res != True:breakend = time.time()seconds = end - startif seconds < 1.0/fps:time.sleep(1.0/fps - seconds)cv2.imshow('img', cur_frame)key = cv2.waitKey(30) & 0xffif key == 27:breakgray_img = cv2.cvtColor(cur_frame, cv2.COLOR_BGR2GRAY)gray_img = cv2.resize(gray_img, (500, 500))gray_img = cv2.GaussianBlur(gray_img, (21, 21), 0)if pre_frame is None:pre_frame = gray_imgelse:img_delta = cv2.absdiff(pre_frame, gray_img)thresh = cv2.threshold(img_delta, 25, 255, cv2.THRESH_BINARY)[1]thresh = cv2.dilate(thresh, None, iterations=2)image, contours, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)for c in contours:if cv2.contourArea(c) < 1000: # 設置敏感度continueelse:#print(cv2.contourArea(c))print("前一幀和當前幀不一樣了, 有什么東西在動!")play_music = Truebreakpre_frame = gray_imgcamera.release() cv2.destroyAllWindows()

?

加入人臉識別

import cv2 import timesave_path = './face/' face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml') eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')camera = cv2.VideoCapture(0) # 參數0表示第一個攝像頭# 判斷視頻是否打開 if (camera.isOpened()):print('Open') else:print('攝像頭未打開')# 測試用,查看視頻size size = (int(camera.get(cv2.CAP_PROP_FRAME_WIDTH)),int(camera.get(cv2.CAP_PROP_FRAME_HEIGHT))) print('size:'+repr(size))fps = 5 # 幀率 pre_frame = None # 總是取視頻流前一幀做為背景相對下一幀進行比較 i = 0 while True:start = time.time()grabbed, frame_lwpCV = camera.read() # 讀取視頻流gray_lwpCV = cv2.cvtColor(frame_lwpCV, cv2.COLOR_BGR2GRAY) # 轉灰度圖if not grabbed:breakend = time.time()# 人臉檢測部分faces = face_cascade.detectMultiScale(gray_lwpCV, 1.3, 5)for (x, y, w, h) in faces:cv2.rectangle(frame_lwpCV, (x, y), (x + w, y + h), (255, 0, 0), 2)roi_gray_lwpCV = gray_lwpCV[y:y + h // 2, x:x + w] # 檢出人臉區域后，取上半部分，因為眼睛在上邊啊，這樣精度會高一些roi_frame_lwpCV = frame_lwpCV[y:y + h // 2, x:x + w]cv2.imwrite(save_path + str(i) + '.jpg', frame_lwpCV[y:y + h, x:x + w]) # 將檢測到的人臉寫入文件i += 1eyes = eye_cascade.detectMultiScale(roi_gray_lwpCV, 1.03, 5) # 在人臉區域繼續檢測眼睛for (ex, ey, ew, eh) in eyes:cv2.rectangle(roi_frame_lwpCV, (ex, ey), (ex + ew, ey + eh), (0, 255, 0), 2)cv2.imshow('lwpCVWindow', frame_lwpCV)# 運動檢測部分seconds = end - startif seconds < 1.0 / fps:time.sleep(1.0 / fps - seconds)gray_lwpCV = cv2.resize(gray_lwpCV, (500, 500))# 用高斯濾波進行模糊處理，進行處理的原因：每個輸入的視頻都會因自然震動、光照變化或者攝像頭本身等原因而產生噪聲。對噪聲進行平滑是為了避免在運動和跟蹤時將其檢測出來。gray_lwpCV = cv2.GaussianBlur(gray_lwpCV, (21, 21), 0) # 在完成對幀的灰度轉換和平滑后，就可計算與背景幀的差異，并得到一個差分圖（different map）。還需要應用閾值來得到一幅黑白圖像，并通過下面代碼來膨脹（dilate）圖像，從而對孔（hole）和缺陷（imperfection）進行歸一化處理if pre_frame is None:pre_frame = gray_lwpCVelse:img_delta = cv2.absdiff(pre_frame, gray_lwpCV)thresh = cv2.threshold(img_delta, 25, 255, cv2.THRESH_BINARY)[1]thresh = cv2.dilate(thresh, None, iterations=2)image, contours, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)for c in contours:if cv2.contourArea(c) < 1000: # 設置敏感度continueelse:print("咦,有什么東西在動")breakpre_frame = gray_lwpCVkey = cv2.waitKey(1) & 0xFF# 按'q'健退出循環if key == ord('q'):break # When everything done, release the capture camera.release() cv2.destroyAllWindows()

?

用同事做了一下實驗，hahahahhhh

附件

https://files.cnblogs.com/files/botoo/%E6%96%87%E4%BB%B6.rar

?

轉載于:https://www.cnblogs.com/botoo/p/9722155.html

總結

以上是生活随笔為你收集整理的【树莓派编程】检测有没有物体移动 +人脸识别的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。