QQ客服 官方微博 反馈留言

	Occlusion handling with 1-regularized sparse reconstruction
	Li, Wei ; Li, Bing ; Zhang, Xiaoqin ; Hu, Weiming ; Wang, Han ; Luo, Guan ; Wang HZ(王菡子)
	2011
关键词	Algorithms Bayesian networks Inference engines
英文摘要	Conference Name:10th Asian Conference on Computer Vision, ACCV 2010. Conference Address: Queenstown, New zealand. Time:November 8, 2010 - November 12, 2010.; The Asian Federation of Computer Vision Societies (AFCV); NextWindow-Touch-Screen Technology; Areograph - Interactive Computer Graphics; Microsoft Research Asia; Australia's Information and Communications Technology(NICTA); Tracking multi-object under occlusion is a challenging task. When occlusion happens, only the visible part of occluded object can provide reliable information for the matching. In conventional algorithms, the deducing of the occlusion relationship is needed to derive the visible part. However deducing the occlusion relationship is difficult. The inter-determined effect between the occlusion relationship and the tracking results will degenerate the tracking performance, and even lead to the tracking failure. In this paper, we propose a novel framework to track multi-object with occlusion handling according to sparse reconstruction. The matching with 1-regularized sparse reconstruction can automatically focus on the visible part of the occluded object, and thus exclude the need of deducing the occlusion relationship. The tracking is simplified into a joint Bayesian inference problem. We compare our algorithm with the state-of-the-art algorithms. The experimental results show the superiority of our algorithm over other competing algorithms. ? 2011 Springer-Verlag Berlin Heidelberg.
语种	英语
出处	http://dx.doi.org/10.1007/978-3-642-19282-1_50
出版者	Springer Verlag
内容类型	其他
源URL	[http://dspace.xmu.edu.cn/handle/2288/87063]
专题	信息技术－会议论文
推荐引用方式 GB/T 7714	Li, Wei,Li, Bing,Zhang, Xiaoqin,et al. Occlusion handling with 1-regularized sparse reconstruction. 2011-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。