python+opencv实现移动侦测（帧差法）
本⽂实例为⼤家分享了python+opencv实现移动侦测的具体代码，供⼤家参考，具体内容如下
1.帧差法原理
移动侦测即是根据视频每帧或者⼏帧之间像素的差异，对差异值设置阈值，筛选⼤于阈值的像素点，做掩模图即可选出视频中存在变化的桢。帧差法较为简单的视频中物体移动侦测，帧差法分为：单帧差、两桢差、和三桢差。随着帧数的增加是防⽌检测结果的重影。
2.算法思路
⽂章以截取视频为例进⾏单帧差法移动侦测
3.python实现代码
def threh(video,save_video,thres1,area_threh):
cam = cv2.VideoCapture(video)#打开⼀个视频
input_fps = (cv2.CAP_PROP_FPS)
ret_val, input_image = ad()
index=[]
images=[]
images.append(input_image)
video_length = (cv2.CAP_PROP_FRAME_COUNT))
input_size(input_image,(512,512))
ending_frame = video_length
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(save_video,fourcc, input_fps, (512, 512))
gray_lwpCV = cv2.cvtColor(input_image, cv2.COLOR_BGR2GRAY)
gray_lwpCV = cv2.GaussianBlur(gray_lwpCV, (21, 21), 0)
background=gray_lwpCV
# es = StructuringElement(cv2.MORPH_ELLIPSE, (9, 4))
i = 0 # default is 0
outt=[]
while(cam.isOpened()) and ret_val == True and i <2999:
## if i % 2==1:
ret_val, input_image = ad()
input_size(input_image,(512,512))
gray_lwpCV = cv2.cvtColor(input_image, cv2.COLOR_BGR2GRAY)
gray_lwpCV = cv2.GaussianBlur(gray_lwpCV, (21, 21), 0)
diff = cv2.absdiff(background, gray_lwpCV)
outt.append(diff)
#跟着图像变换背景
tem_diff=diff.flatten()
tem_ds=pd.Series(tem_diff)
tem_per=1-len(tem_ds[tem_ds==0])/len(tem_ds)
if (tem_per <0.2 )| (tem_per>0.75):
background=gray_lwpCV
else:
diff = cv2.threshold(diff, thres1, 255, cv2.THRESH_BINARY)[1]
ret,thresh = cv2.py(),150,255,0)
contours, hierarchy = cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
#  contours, hierarchy = cv2.py(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
for c in contours:
if (urArea(c) < area_threh) | (urArea(c) >int(512*512*0.3) ) :  # 对于矩形区域，只显⽰⼤于给定阈值的轮廓（去除微⼩的变化等噪点）    continue
(x, y, w, h) = cv2.boundingRect(c) # 该函数计算矩形的边界框rectangle函数opencv
index.append(i)
#  cv2.imshow('contours', input_image)
#  cv2.imshow('dis', diff)
out.write(input_image)
images.append(input_image)
i = i+1
return outt,index,images```
##调取函数
outt=threh('new_video.mp4','test6.mp4',25,3000)
以上就是本⽂的全部内容，希望对⼤家的学习有所帮助，也希望⼤家多多⽀持。

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。