Object Tracking via Online Metric Learning

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Object Tracking via Online Metric Learning
	Cong Y(丛杨); Yuan JS(袁浚菘); Tang YD(唐延东)
	2012
会议名称	2012 IEEE International Conference on Image Processing
会议日期	September 30 - October 3, 2012
会议地点	Orland, Florida, USA
关键词	tracking metric learning semi-supervised learning online learning
页码	417-420
通讯作者	丛杨
中文摘要	By considering visual tracking as a similarity matching problem, we propose a self-supervised tracking method that incorporates adaptive metric learning and semi-supervised learning into the framework of object tracking. For object representation, the spatial-pyramid structure is applied by fusing both the shape and texture cues as descriptors. A metric learner is adaptively trained online to best distinguish the foreground object and background, and a new bi-linear graph is defined accordingly to propagate the label of each sample. Then high-confident samples are collected to self-update the model to handle large-scale issue. Experiments on the benchmark dataset and comparisons with the state-of-the-art methods validate the advantages of our algorithm.
收录类别	EI ; CPCI（ISTP）
产权排序	1
会议主办者	IEEE Signal Processing Society
会议录	Proceedings of the 2012 IEEE International Conference on Image Processing
会议录出版者	IEEE
会议录出版地	New York, USA
语种	英语
ISBN号	978-1-4673-2533-2
WOS记录号	WOS:000319334900100
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/10212]
专题	沈阳自动化研究所_机器人学研究室
推荐引用方式 GB/T 7714	Cong Y,Yuan JS,Tang YD. Object Tracking via Online Metric Learning[C]. 见:2012 IEEE International Conference on Image Processing. Orland, Florida, USA. September 30 - October 3, 2012.