Aligned Spatial-Temporal Memory Network for Thermal Infrared Target Tracking

被引:61
作者
Yuan, Di [1 ]
Shu, Xiu [2 ]
Liu, Qiao [3 ]
He, Zhenyu [4 ]
机构
[1] Xidian Univ, Guangzhou Inst Technol, Guangzhou 510555, Peoples R China
[2] Harbin Inst Technol, Sch Sci, Shenzhen 518055, Peoples R China
[3] Chongqing Normal Univ, Natl Ctr Appl Math, Chongqing 401331, Peoples R China
[4] Harbin Inst Technol, Sch Comp Sci & Technol, Shenzhen 518055, Peoples R China
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
Target tracking; Task analysis; Training; Interference; Benchmark testing; Feature extraction; Convolution; Thermal infrared tracking; spatial-temporal memory network; aligned matching module; OBJECT TRACKING;
D O I
10.1109/TCSII.2022.3223871
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
Thermal infrared (TIR) target tracking is susceptible to occlusion and similarity interference, which obviously affects the tracking results. To resolve this problem, we develop an Aligned Spatial-Temporal Memory network-based Tracking method (ASTMT) for the TIR target tracking task. Specifically, we model the scene information in the TIR target tracking scenario using the spatial-temporal memory network, which can effectively store the scene information and decrease the interference of similarity interference that is beneficial to the target. In addition, we use an aligned matching module to correct the parameters of the spatial-temporal memory network model, which can effectively alleviate the impact of occlusion on the target estimation, hence boosting the tracking accuracy even further. Through ablation study experiments, we have demonstrated that the spatial-temporal memory network and the aligned matching module in the proposed ASTMT tracker are exceptionally successful. Our ASTMT tracking method performs well on the PTB-TIR and LSOTB-TIR benchmarks contrasted with other tracking methods.
引用
收藏
页码:1224 / 1228
页数:5
相关论文
共 45 条
[1]  
Bhat Goutam, 2020, Computer Vision - ECCV 2020. 16th European Conference. Proceedings. Lecture Notes in Computer Science (LNCS 12368), P205, DOI 10.1007/978-3-030-58592-1_13
[2]   Learning Discriminative Model Prediction for Tracking [J].
Bhat, Goutam ;
Danelljan, Martin ;
Van Gool, Luc ;
Timofte, Radu .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :6181-6190
[3]   Ramp-Tracking Generalized Predictive Control System-Based on Second-Order Difference [J].
Cordero, R. ;
Estrabis, T. ;
Batista, E. A. ;
Andrea, C. Q. ;
Gentil, G. .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2021, 68 (04) :1283-1287
[4]   Fixed-Time Prescribed Performance Adaptive Trajectory Tracking Control for a QUAV [J].
Cui, Guozeng ;
Yang, Wei ;
Yu, Jinpeng ;
Li, Ze ;
Tao, Chongben .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2022, 69 (02) :494-498
[5]   ATOM: Accurate Tracking by Overlap Maximization [J].
Danelljan, Martin ;
Bhat, Goutam ;
Khan, Fahad Shahbaz ;
Felsberg, Michael .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :4655-4664
[6]   Learning Spatially Regularized Correlation Filters for Visual Tracking [J].
Danelljan, Martin ;
Hager, Gustav ;
Khan, Fahad Shahbaz ;
Felsberg, Michael .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :4310-4318
[7]   Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking [J].
Dong, Xingping ;
Shen, Jianbing ;
Wang, Wenguan ;
Shao, Ling ;
Ling, Haibin ;
Porikli, Fatih .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (05) :1515-1529
[8]   Triplet Loss in Siamese Network for Object Tracking [J].
Dong, Xingping ;
Shen, Jianbing .
COMPUTER VISION - ECCV 2018, PT XIII, 2018, 11217 :472-488
[9]  
Galoogahi HK, 2017, IEEE I CONF COMP VIS, P1144, DOI [10.1109/ICCV.2017.128, 10.1109/ICCV.2017.129]
[10]   Infrared Target Tracking Using Multi-Feature Joint Sparse Representation [J].
Gao, Shu Juan ;
Jhang, Seong Tae .
2016 RESEARCH IN ADAPTIVE AND CONVERGENT SYSTEMS, 2016, :40-45