摘要
针对经典的Mean Shift算法在目标部分遮挡或者场景光照变化时容易出现跟踪目标丢失的问题,文章运用一种基于分块权重的方法处理目标部分遮挡问题,每一部分的权重系数由来自不同的块和背景颜色信息共同决定.为了适应场景光照的变化,提出快速并且稳定的更新机制.实验分析,该方法可实现快速有效的跟踪.
Traditional mean shift tracking algorithm which could not work well when the target is under partial occlusion and illumination variations.In this paper,we propose a weighted fragment based approach that tackles partial occlusion.The weights are derived from the difference between background colors and the fragment.A fast and stable model update method is described for the sake of illumination variations.Experimental results show that this method can achieve fast and efficient tracking.
出处
《广西民族大学学报（自然科学版）》
CAS
2012年第1期50-54,共5页
Journal of Guangxi Minzu University ：Natural Science Edition
基金
广西自然科学基金(2012GXNSFAA053227)
