Python+OpenCV目標跟蹤實現(xiàn)基本的運動檢測

import cv2
import numpy as np

camera = cv2.VideoCapture(0) # 參數(shù)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))

es = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9, 4))
kernel = np.ones((5, 5), np.uint8)
background = None

while True:
  # 讀取視頻流
  grabbed, frame_lwpCV = camera.read()
  # 對幀進行預處理，先轉灰度圖，再進行高斯濾波。
  # 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(chǎn)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.cvtColor(frame_lwpCV, cv2.COLOR_BGR2GRAY)
  gray_lwpCV = cv2.GaussianBlur(gray_lwpCV, (21, 21), 0)

  # 將第一幀設置為整個輸入的背景
  if background is None:
    background = gray_lwpCV
    continue
  # 對于每個從背景之后讀取的幀都會計算其與北京之間的差異，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
  diff = cv2.absdiff(background, gray_lwpCV)
  diff = cv2.threshold(diff, 25, 255, cv2.THRESH_BINARY)[1] # 二值化閾值處理
  diff = cv2.dilate(diff, es, iterations=2) # 形態(tài)學膨脹

  # 顯示矩形框
  image, contours, hierarchy = cv2.findContours(diff.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) # 該函數(shù)計算一幅圖像中目標的輪廓
  for c in contours:
    if cv2.contourArea(c) < 1500: # 對于矩形區(qū)域，只顯示大于給定閾值的輪廓，所以一些微小的變化不會顯示。對于光照不變和噪聲低的攝像頭可不設定輪廓最小尺寸的閾值
      continue
    (x, y, w, h) = cv2.boundingRect(c) # 該函數(shù)計算矩形的邊界框
    cv2.rectangle(frame_lwpCV, (x, y), (x+w, y+h), (0, 255, 0), 2)

  cv2.imshow('contours', frame_lwpCV)
  cv2.imshow('dis', diff)

  key = cv2.waitKey(1) & 0xFF
  # 按'q'健退出循環(huán)
  if key == ord('q'):
    break
# When everything done, release the capture
camera.release()
cv2.destroyAllWindows()