Object Tracking Using Multiple Features and Adaptive Model Updating

doi:10.1109/TIM.2017.2729378

	Object Tracking Using Multiple Features and Adaptive Model Updating
	Hu, Qingyong 1; Guo, Yulan 1,2; Lin, Zaiping 1; An, Wei 1; Cheng, Hongwei 1
	2017-11-01
发表期刊	IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
ISSN	0018-9456
卷号	66 期号:11 页码:2882-2897
摘要	Correlation filter-based tracking methods have been intensively investigated for their high efficiency and robustness. However, a single feature-based tracker cannot adapt to challenging situations, such as severe deformation, rotation, and illumination variations. Besides, a simple linear interpolation-based model updating mechanism is prone to model degradation, and consequently tracker drifting. In this paper, a 2-D location filter is combined with a 1-D scale filter to jointly estimate the state of object under tracking, and three complementary features are integrated to further enhance the overall tracking performance. Besides, we define a penalty factor for adaptive model updating, to achieve a balance between stability and flexibility, especially when the object is under occlusion. Extensive experiments have been conducted on four large-scale data sets, namely, the object tracking benchmark, VOT15, Temple-Color128, and the UAV123 tracking benchmark. Quantitative and qualitative results show that our proposed tracker achieves promising results in terms of tracking accuracy, robustness, and speed as compared with other popular trackers, and is highly suitable for real-time applications, such as unmanned aerial vehicles. It outperforms the state-of-the-art methods under different nuisances, including scale variation, deformation, occlusion, rotation, and out-of-view.
关键词	Adaptive model updating correlation filters multiple feature integration object tracking
DOI	10.1109/TIM.2017.2729378
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61602499] ; National Natural Science Foundation of China[61471371] ; National Postdoctoral Program for Innovative Talents[BX201600172] ; China Postdoctoral Science Foundation
WOS研究方向	Engineering ; Instruments & Instrumentation
WOS类目	Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号	WOS:000412573300010
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：23[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/6782
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Guo, Yulan
作者单位	1.Natl Univ Def Technol, Coll Elect Sci & Engn, Changsha 410073, Hunan, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Hu, Qingyong,Guo, Yulan,Lin, Zaiping,et al. Object Tracking Using Multiple Features and Adaptive Model Updating[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2017,66(11):2882-2897.
APA	Hu, Qingyong,Guo, Yulan,Lin, Zaiping,An, Wei,&Cheng, Hongwei.(2017).Object Tracking Using Multiple Features and Adaptive Model Updating.IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,66(11),2882-2897.
MLA	Hu, Qingyong,et al."Object Tracking Using Multiple Features and Adaptive Model Updating".IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 66.11(2017):2882-2897.