To realize the accurate extraction of the moving object in the surveillance video , since the traditional three frame difference method can not avoid"hollow"w hile detecting the moving object ,an algorithm that based on three frame difference and mean background is proposed .T he algorithm is that by using the background of the current frame of the video to difference with the current frame of the video and the next frame of the video to make the three frame difference method avoid the influence of the background pixels in the process of moving object detection and eliminate the "hole" phenomenon .The simulation results show that the proposed method performs better than the traditional algorithms and moving object can be detected quickly in complicated background circumstances .%为了实现对室外监控视频中人体运动目标的准确提取,针对传统的三帧差分法在运动目标检测过程中容易出现"空洞"现象,提出了一种基于均值背景与三帧差分的运动目标检测算法.该算法通过将经均值背景建模得到的视频当前帧的背景加入到三帧差分中与视频当前帧和视频当前帧的下一帧分别进行邻间差分,避免了背景像素点对前景检测带来的影响,解决了三帧差分法在运动目标检测过程中存在的"空洞"问题.仿真结果表明,该算法在完整性和准确性方面要优于传统的运动目标检测算法,可以在复杂背景环境中实现快速的运动目标提取.
展开▼