Regression-Selective Feature-Adaptive Tracker for Visual Object Tracking

作     者：Zhou, Ze Sun, Quansen Li, Hongjun Li, Chaobo Ren, Zhenwen 

作者机构：Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong 226019 Jiangsu Peoples R China Southwest Univ Sci & Technol Sch Natl Def Sci & Technol Mianyang 621010 Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON MULTIMEDIA》 (IEEE Trans Multimedia)

年 卷 期：2023年第25卷

页      面：5444-5457页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Science Foundation of China [61802188, 61673220, 61976028] Natural Science Foundation of Jiangsu Province [BK20180458] Nantong Science and Technology Program [JC2021131] 

主　　题：Visual object tracking Refined criterion Adaptive receptive field Centrality Online update 

摘      要：As a challenging visual task, visual object tracking has recently been composed of the classification and regression subtasks. The anchor-free regression network gets rid of the dependence on the anchors, but the redundant range makes it usually regress some samples involving non-target information. Evenly dividing a target by the regular receptive field often causes ambiguous target localization. To address these issues, we propose a regression-selective feature-adaptive tracker (RSFA), where the regression-selective subnetwork can not only free the regression task from anchors, but can also select more effective regression samples using the refined criterion. The proposed feature-adaptive strategy concentrates the classification subnetwork on target feature extraction via adaptively modifying the receptive field, and the attached centrality branch offers a correction for target localization by exploiting the spatial information. Additionally, the designed online update mechanism realizes the tracker s online optimization, improving robustness against target deformation. Extensive experiments are conducted on challenging benchmarks, including GOT10 K, OTB2015, UAV123, NFS, VOT2018, VOT2019 and VOT2020-ST. Our tracker achieves satisfactory tracking results, and the evaluations of its tracking performance rank first or second in comparison with the state-of-the-art tracking algorithms.