中文摘要：

在假定背景像素以较高频率在图像序列中出现的前提下,利用DWT变换的多分辨率优点,提出一种自适应在线聚类的运动目标提取方法。首先将待处理的视频图像序列经过DWT变换提取近似分量;然后利用像素点聚类方法,结合自适应动态阈值和相似类合并来重构背景;最后借鉴图像匹配的评价标准验证重构背景的准确性。实验结果表明,该方法能够准确快速地提取运动目标,并对环境变化、目标迂回移动、多目标运动情况具有较好的鲁棒性

英文摘要：

Based on the hypothesis that the background pixel intensity appears in image sequence with maximum probability,this paper proposed a novel method of moving objects extracting by utilizing the merits of multi-resolution of DWT.The method extracted the approximate components of video images sequence firstly using the DWT,and then reconstruced the background according to the pixels clustering combing adaptively dynamic threshold with similar classes merged,verified the accuracy of background reconstruction by quoting the evaluation criteria of image matches.Experimental results indicate that the proposed method can extract the motion objects correctly and fast,even in the cases of environments change,moving targets roundabout,multi-targets moving