Particle filter based visual tracking with multi-cue adaptive fusion
作者： Anping Li , Zhongliang Jing , Shiqiang Hu
DOI:
关键词:
摘要: To improve the robustness of visual tracking in complex environments such as: cluttered backgrounds, partial occlusions, similar distraction and pose variations, a novel method based on adaptive fusion particle filter is proposed this paper. In method, image color shape cues are adaptively fused to represent target observation; fuzzy logic applied dynamically adjust each cue weight according its associated reliability past frame; adopted deal with non-linear non-Gaussian problems tracking. The demonstrated be robust illumination changes, backgrounds camera motion for test sequence.
harvard.edu
osapublishing.org参考文章(0)