基于色块边缘和颜色直方图的多目标跟踪算法

摘要

基于颜色直方图的人体跟踪是最为常用的跟踪方法. 但是在人数较多的场景下,仅靠颜色直方图难以准确描述目标特征. 对此,提出一种基于色块边缘统计和颜色直方图的多目标实时跟踪算法,利用色块边缘分布和颜色特征对目标进行匹配,通过卡尔曼滤波确定搜索范围,并对跟踪过程进行并行化处理. 实验结果表明,该算法可以有效地提高多目标跟踪的准确率和鲁棒性.%Human tracking based on the color histogram is one of the most popular tracking methods .However,it is hard to accu-rately describe the target signature in bigger number of people scene if it solely depends on the color histogram .Therefore,we propose a multi-target real t-ime tracking algorithm based on the color edge statistics and the color histogram .Furthermore,this al-gorithm can deal with the tracking process ,match the target by the color edge distribution and the color characteristics , and con-firm the scope of target searching .The experimental results show that the algorithm can effectively improve the multi-target track-ing accuracy and robustness .