Multi-object tracking via MHT with multiple information fusion in surveillance video

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Multi-object tracking via MHT with multiple information fusion in surveillance video
	Ying, Long; Zhang, Tianzhu; Xu, Changsheng
刊名	MULTIMEDIA SYSTEMS
	2015-06-01
卷号	21 期号:3 页码:313-326
关键词	Multi-object tracking Data association MHT Multiple information fusion
英文摘要	Tracking multiple objects is critical to automatic video content analysis and virtual reality. The major problem is how to solve data association problem when ambiguous measurements are caused by objects in close proximity. To tackle this problem, we propose a multiple information fusion-based multiple hypotheses tracking algorithm integrated with appearance feature, local motion pattern feature and repulsion-inertia model for multi-object tracking. Appearance model based on HSV-local binary patterns histogram and local motion pattern based on optical flow are adopted to describe objects. A likelihood calculation framework is proposed to incorporate the similarities of appearance, dynamic process and local motion pattern. To consider the changes in appearance and motion pattern over time, we make use of an effective template updating strategy for each object. In addition, a repulsioninertia model is adopted to explore more useful information from ambiguous detections. Experimental results show that the proposed approach generates better trajectories with less missing objects and identity switches.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Information Systems ; Computer Science, Theory & Methods
研究领域[WOS]	Computer Science
关键词[WOS]	ALGORITHM ; ASSOCIATION ; MODEL
收录类别	SCI
语种	英语
WOS记录号	WOS:000355813200008
公开日期	2015-09-22
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/7931]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ying, Long,Zhang, Tianzhu,Xu, Changsheng. Multi-object tracking via MHT with multiple information fusion in surveillance video[J]. MULTIMEDIA SYSTEMS,2015,21(3):313-326.
APA	Ying, Long,Zhang, Tianzhu,&Xu, Changsheng.(2015).Multi-object tracking via MHT with multiple information fusion in surveillance video.MULTIMEDIA SYSTEMS,21(3),313-326.
MLA	Ying, Long,et al."Multi-object tracking via MHT with multiple information fusion in surveillance video".MULTIMEDIA SYSTEMS 21.3(2015):313-326.