BackgroundSubtractorMOG

MOG算法，即高斯混合模型分离算法，它使用一种通过K高斯分布的混合来对每个背景像素进行建模的方法(K = 3-5）

import numpy as npimport cv2import matplotlib.pyplot as pltcap = cv2.VideoCapture('test.mp4')fgbg = cv2.bgsegm.createBackgroundSubtractorMOG()while(1):    ret, frame = cap.read()    fgmask = fgbg.apply(frame)    cv2.imshow('frame',fgmask)    k = cv2.waitKey(30) & 0xff    if k == 27:        breakcap.release()cv2.destroyAllWindows()

BackgroundSubtractorMOG2

MOG2算法，也是高斯混合模型分离算法，是MOG的改进算法,该算法的一个重要特征是 它为每个像素选择适当数量的高斯分布，它可以更好地适应不同场景的照明变化等.

import numpy as npimport cv2import matplotlib.pyplot as pltcap = cv2.VideoCapture('test.mp4')fgbg = cv2.createBackgroundSubtractorMOG2()while(1):    ret, frame = cap.read()    fgmask = fgbg.apply(frame)    cv2.imshow('frame',fgmask)    k = cv2.waitKey(30) & 0xff    if k == 27:        breakcap.release()cv2.destroyAllWindows()

BackgroundSubtractorGMG

该算法结合统计背景图像估计和每像素贝叶斯分割,该算法使用前几个（默认为120）帧进行后台建模。它采用概率前景分割算法，使用贝叶斯推理识别可能的前景对象.在前几帧图像中会得到一个黑色窗口.

import numpy as npimport cv2import matplotlib.pyplot as pltcap = cv2.VideoCapture('test.mp4')kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(3,3))fgbg = cv2.bgsegm.createBackgroundSubtractorGMG()while(1):    ret, frame = cap.read()    fgmask = fgbg.apply(frame)    fgmask = cv2.morphologyEx(fgmask, cv2.MORPH_OPEN, kernel)    cv2.imshow('frame',fgmask)    k = cv2.waitKey(30) & 0xff    if k == 27:        breakcap.release()cv2.destroyAllWindows()