视频序列中运动目标自动提取的研究  

Research on Automatic Segmentation of Moving Object in Video Sequences

作　　者：李庆忠[1] 刘怀强 侯永海[1] 褚东升[1] 

机构地区：[1]中国海洋大学工程学院,青岛266071

出　　处：《微计算机信息》2006年第05S期246-247,305,共3页Control & Automation

基　　金：国家自然科学基金(A0324676)资助

摘　　要：本文提出了一种从彩色视频序列中,有效分割运动目标的算法。首先将当前帧图像和背景参考图像在YUV彩色空间中进行距离差分得到距离差分图像,然后根据差分图像直方图的单峰聚集特性,提出了基于直方图的自适应聚类分割算法;对分割后的二值图像采用图像形态学方法去除无用的噪声斑点,并根据得到运动模板,提出了背景参考图像的更新策略。实验结果表明这是一种简单、有效的运动目标提取方法。This paper presents an effective segmentation method for moving objects in color video sequences. The difference image of color distance between current image and the reference background image in YUV color space is first obtained. According to the mono-modal feature of histogram of the difference image, we propose an adaptive clustering segmentation method based on histogram. The image morphology filtering is employed to remove the flecks of noise existed in the segmented binary image. Finally, an updating scheme for background image is introduced to follow the variation of illumination conditions and changes in environmental conditions. Experimental results show that the proposed method is simple and effective in extracting moving objects from video sequences.

关 键 词：图像处理 图像分割 目标提取 图像形态学 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]