电子学报2011，Vol.39Issue(2)：260-267,8.
一种基于交互式粒子滤波器的视频中多目标跟踪算法
Interactive Particle Filter Based Algorithm for Tracking Multiple Objects in Videos
摘要
Abstract
When tracking multiple objects,prior models such as path comsistency assumption model are generally established in order to handle occlusion problems. However,if the assumption is greatly distinguished from the real trajectories of the objects,the tracker is doomed to fail. To solve this problem,we put forward a definition of interactive particle filter which adaptively selects appearance template for a particle to measure its likelibood by judging the occluding relationship between each two samples of different objects. The experiments illustrate that our method accurately locates the object even if it is completely occluded as well as the trajectory is impossible to be predicted.关键词
多目标跟踪/交互式粒子滤波/目标遮挡/外观模板选择Key words
multiple objects tracking/interactive particle filter/occlusion/observation template selection分类
信息技术与安全科学引用本文复制引用
刘晨光,程丹松,刘家锋,黄剑华,唐降龙..一种基于交互式粒子滤波器的视频中多目标跟踪算法[J].电子学报,2011,39(2):260-267,8.基金项目
国家自然科学基金(No.60672090) （No.60672090）
哈尔滨工业大学科研创新基金(No.HIT.NSRIF.2009159) （No.HIT.NSRIF.2009159）
