Support vector correlation filter with long-term tracking

doi:10.1007/s11760-018-1310-0

CORC > 合肥物质科学研究院 > 中国科学院合肥物质科学研究院 > 中科院合肥智能机械研究所

	Support vector correlation filter with long-term tracking
	Wang, Zhongpei 1; Wang, Hao 1; Fang, Baofu 1; Xie, Chengjun 2
刊名	SIGNAL IMAGE AND VIDEO PROCESSING
	2018-11-01
卷号	12 期号:8 页码:1541-1549
关键词	Support correlation filter Long-term tracking Re-detection Passive-aggressive algorithm Max response to average response rate
ISSN号	1863-1703
DOI	10.1007/s11760-018-1310-0
通讯作者	Xie, Chengjun(cjxie@iim.ac.cn)
英文摘要	Boosted by the promising advancement of the correlation filter-based tracker, we propose an algorithm called the SLT (support vector correlation filter with long-term tracking) that is based on the new SCF (support vector correlation filter) framework to handle long-term tracking. To perform long-term tracking, we propose using a detector to refine the position that includes occlusion and deformation and is out-of-view. We used a new judgment criterion called the max response to the average response rate (MAR) to activate the re-detection procedure and then exploit the linear support vector machine (SVM) classifier to obtain a positive refinement. Moreover, we do not update the SVM classifier every frame to reduce the number of computations and obtain better samples to improve the accuracy of the classifier. We use the online passive-aggressive learning algorithm for online learning and use the same MAR criterion to active it. Extensive experimental results on the OTB50 benchmark dataset show its superior performance in terms of accuracy and robustness.
资助项目	National Natural Science Foundation of China[61175033]
WOS关键词	OBJECT TRACKING ; ROBUST TRACKING
WOS研究方向	Engineering ; Imaging Science & Photographic Technology
语种	英语
出版者	SPRINGER LONDON LTD
WOS记录号	WOS:000444312400014
资助机构	National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/38837]
专题	合肥物质科学研究院_中科院合肥智能机械研究所
通讯作者	Xie, Chengjun
作者单位	1.Hefei Univ Technol, Sch Comp & Informat, Hefei 230009, Anhui, Peoples R China 2.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Peoples R China
推荐引用方式 GB/T 7714	Wang, Zhongpei,Wang, Hao,Fang, Baofu,et al. Support vector correlation filter with long-term tracking[J]. SIGNAL IMAGE AND VIDEO PROCESSING,2018,12(8):1541-1549.
APA	Wang, Zhongpei,Wang, Hao,Fang, Baofu,&Xie, Chengjun.(2018).Support vector correlation filter with long-term tracking.SIGNAL IMAGE AND VIDEO PROCESSING,12(8),1541-1549.
MLA	Wang, Zhongpei,et al."Support vector correlation filter with long-term tracking".SIGNAL IMAGE AND VIDEO PROCESSING 12.8(2018):1541-1549.