视频图像序列中运动目标区域检测算法研究  

Research of Moving Object Area Detection in Video Image Sequence

作　　者：杜岳涛[1] 张学智[1] 

机构地区：[1]西安工业大学电子信息工程学院,西安710032

出　　处：《计算机与数字工程》2012年第8期107-109,共3页Computer & Digital Engineering

摘　　要：文章针对视频图像的特点,提出一种基于背景差分法的运动目标区域检测算法。该算法利用当前图像与背景图像作差分,并采用一阶Kalman滤波实现动态背景图像的更新,接着采用自适应阈值法进行运动区域分割,经过滤波处理即可得到运动目标区域。实验结果表明所提出的算法具有较理想的效果。According to thecharacter of video image,a detection algorithm of moving object area based on background difference is proposed in this paper.The algorithm use the current image and background image to make the difference firstly,and then using the first-order Kalman filter to make the refresh of dynamic background image.After this,a self-adapting threshold is used in region segmentation,moving object area after filter processing can be obtained.The experiment result shows that this algorithm proposed in this paper has very good effect.

关 键 词：视频图像 背景差分 背景更新 自适应阈值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]