一种融合了信念传播思想的背景分割优化方法.pdfVIP

中国科技论文在线 一种融合了信念传播思想的背景分割优化 方法 王红，武文斌，张静文，毋立芳，范国强 （北京工业大学电子信息与控制学院，北京 100124 ） 摘要：背景分割问题是目标检测、目标跟踪、目标识别、目标理解等一系列运动分析的首要 步骤。为了解决目前分割结果中出现的“空洞”现象，提出了将改进的Codebook 背景建模方 法和置信传播思想相融合的优化背景分割方法。首先，利用改进了匹配条件的Codebook 背 景建模算法对场景进行建模，减少边缘区域和场景较暗区域的噪声，得到初始的分割结果； 然后，基于置信传播思想，通过消息传递，加强像素之间的关联，平滑初始背景分割结果中 出现的“空洞”现象，达到优化的目的；最后，通过举重训练图像分别检测算法的有效性，证 明优化分割方法可以很好的填充Codebook 背景建模方法的分割结果中出现的“空洞”现象。 关键词：信号与信息处理；背景分割；码本建模；置信传播 中图分类号：TP391 文献标识码：A An optimized background segmentation method combining belief propagation thought Wang Hong, Wu Wenbin, Zhang Jingwen, Wu Lifang, Fan Guoqiang (School of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China) Abstract: Although there are many background segmentation methods, relationships among pixels are often ignored in these methods, resulting in the “hole” in the extracted object. An approach combining codebook scheme and belief propagation scheme to optimize the segmentation object has been proposed. Firstly, the background scene is modeled using codebook scheme with improved matching conditions and the initial object is extracted. Then the optimal belief propagation scheme is used which could fill the hole in the initial segmentation. Finally, the optimized approach is tested using practical video of weight-lifting. For the practical video, it could obtain the initial segmentations and the optimization. These results show that the optimized approach can obtain more complete segmentation. Key words: signal and information processing; background segmentation; codebook; belief propagation 视频中的背景分割广泛应用于与视频监控相关的多种智能系统中，背景分割的质量直接 影响对所关注目标的检测、跟踪、识别、理解等一系列运动分析结果的准确性。在众多的背 景分割方法中，背景建模方法通过对背景像素进行建模，更新适应背景的变化，鲁棒性较好。 目前有很多