【樹莓派編程】檢測有沒有物體移動 +人臉識別

時間 2019-11-12

原文原文鏈接

檢測有沒有物體移動ide

import cv2
import time
 
camera = cv2.VideoCapture(0)
if camera is None:
    print('請先鏈接攝像頭')
    exit()
 
fps = 5 # 幀率
pre_frame = None  # 老是取前一幀作爲背景（不用考慮環境影響）
 
play_music = False
 
while True:
    start = time.time()
    res, cur_frame = camera.read()
    if res != True:
        break
    end = time.time()
    seconds = end - start
    if seconds < 1.0/fps:
        time.sleep(1.0/fps - seconds)

    cv2.imshow('img', cur_frame)
    key = cv2.waitKey(30) & 0xff
    if key == 27:
        break

    gray_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_img
    else:
        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
                continue
            else:
                #print(cv2.contourArea(c))
                print("前一幀和當前幀不同了, 有什麼東西在動!")
                play_music = True
                break
 
        pre_frame = gray_img
 
camera.release()
cv2.destroyAllWindows()

加入人臉識別測試

import cv2
import time

save_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  # 老是取視頻流前一幀作爲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:
        break
    end = 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] # 檢出人臉區域後，取上半部分，由於眼睛在上邊啊，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 += 1
        eyes = 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 - start
    if 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，進行處理的緣由：每一個輸入的視頻都會因天然震動、光照變化或者攝像頭自己等緣由而產生噪聲。對噪聲進行平滑是爲了不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後，就可計算與背景幀的差別，並獲得一個差分圖（different map）。還須要應用閾值來獲得一幅黑白圖像，並經過下面代碼來膨脹（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_lwpCV
    else:
        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
                continue
            else:
                print("咦,有什麼東西在動")
                break
        pre_frame = gray_lwpCV
    key = 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()