Adaptive Appearance Modeling With Point-to-Set Metric Learning for Visual Tracking

被引:4
作者
Wang, Jun [1 ,2 ]
Wang, Yuanyun [2 ]
Wang, Hanzi [1 ]
机构
[1] Xiamen Univ, Sch Informat Sci & Technol, Fujian Key Lab Sensing & Comp Smart City, Xiamen 361005, Peoples R China
[2] Nanchang Inst Technol, Sch Informat Engn, Nanchang 330099, Jiangxi, Peoples R China
基金
中国国家自然科学基金;
关键词
Affine hull (AH); appearance model; metric learning; visual tracking; FACE RECOGNITION; OBJECT TRACKING; HISTOGRAMS;
D O I
10.1109/TCSVT.2016.2556438
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In visual tracking, developing an efficient appearance model is a challenging task due to the influence of various factors, such as illumination variation, occlusion, background clutter, and so on. Existing tracking algorithms use appearance samples from previous frames to form a template set upon which target appearance models are built. However, these appearance models are data-dependent, so they may be corrupted by significant appearance variation. It is difficult to update the templates in challenging environments. In this paper, we propose a robust visual tracking algorithm with an adaptive appearance model using a point-to-set metric learning technique. To do this, we first model a target representation using a set of target templates and a regularized affine hull (RAH) spanned by the target templates. Then, we learn a point-to-set distance metric, which is incorporated into the optimization process to obtain an adaptive target representation. The RAH model covers unseen target appearances by affine combinations of the target templates. Based on the proposed target appearance model, we design an effective template update scheme by adjusting the weights of the target templates. Experimental results on challenging video sequences with comparisons to several state-of-the-art tracking algorithms demonstrate the effectiveness and robustness of the proposed tracking algorithm.
引用
收藏
页码:1987 / 2000
页数:14
相关论文
共 50 条
[31]   Joint Learning Appearance and Motion Models for Visual Tracking [J].
Xu, Wenmei ;
Yu, Hongyuan ;
Wang, Wei ;
Li, Chenglong ;
Wang, Liang .
PATTERN RECOGNITION AND COMPUTER VISION, PT I, 2021, 13019 :416-428
[32]   Robust tracking with adaptive appearance learning and occlusion detection [J].
Jianwei Ding ;
Yunqi Tang ;
Huawei Tian ;
Wei Liu ;
Yongzhen Huang .
Multimedia Systems, 2016, 22 :255-269
[33]   Appearance Learning by Adaptive Kalman Filters for FLIR Tracking [J].
Venkataraman, Vijay ;
Fan, Guoliang ;
Fan, Xin ;
Havlicek, Joseph P. .
2009 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPR WORKSHOPS 2009), VOLS 1 AND 2, 2009, :312-+
[34]   Discriminative Bag-of-Words-Based Adaptive Appearance Model for Robust Visual Tracking [J].
Zeng, Fanxiang ;
Huang, Zhitong ;
Ji, Yuefeng .
IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (06) :907-911
[35]   Robust adaptive learning with Siamese network architecture for visual tracking [J].
Zhang, Wancheng ;
Du, Yongzhao ;
Chen, Zhi ;
Deng, Jianhua ;
Liu, Peizhong .
VISUAL COMPUTER, 2021, 37 (05) :881-894
[36]   Adaptive Correlation Filters Feature Fusion Learning for Visual Tracking [J].
Yu, Hongtao ;
Zhu, Pengfei .
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2021, PT V, 2021, 12895 :652-664
[37]   Siamese Visual Tracking with Robust Adaptive Learning [J].
Zhang, Wancheng ;
Chen, Zhi ;
Liu, Peizhong ;
Deng, Jianhua .
PROCEEDINGS OF 2019 IEEE 13TH INTERNATIONAL CONFERENCE ON ANTI-COUNTERFEITING, SECURITY, AND IDENTIFICATION (IEEE-ASID'2019), 2019, :153-157
[38]   Adaptive temporal feature modeling for visual tracking via cross-channel learning [J].
Wang, Yuanyun ;
Zhang, Wenshuang ;
Lai, Changwang ;
Wang, Jun .
KNOWLEDGE-BASED SYSTEMS, 2023, 265
[39]   Visual Tracking Based on Adaptive Mean Shift Multiple Appearance Models [J].
Dhassi Y. ;
Aarab A. .
Pattern Recognition and Image Analysis, 2018, 28 (03) :439-449
[40]   Adaptive multi-cue tracking by online appearance learning [J].
Wang, Qing ;
Chen, Feng ;
Xu, Wenli .
NEUROCOMPUTING, 2011, 74 (06) :1035-1045