Visual Tracking via Adaptive Spatially-Regularized Correlation Filters

被引:370
作者
Dai, Kenan [1 ]
Wang, Dong [1 ]
Lu, Huchuan [1 ,2 ]
Sun, Chong [1 ,3 ]
Li, Jianhua [1 ]
机构
[1] Dalian Univ Technol, Sch Informat & Commun Engn, Dalian, Peoples R China
[2] Peng Cheng Lab, Shenzhen, Peoples R China
[3] Tencent Youtu Lab, Shenzhen, Peoples R China
来源
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) | 2019年
基金
中国国家自然科学基金;
关键词
D O I
10.1109/CVPR.2019.00480
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work, we propose a novel adaptive spatially-regularized correlation filters (ASRCF) model to simultaneously optimize the filter coefficients and the spatial regularization weight. First, this adaptive spatial regularization scheme could learn an effective spatial weight for a specific object and its appearance variations, and therefore result in more reliable filter coefficients during the tracking process. Second, our ASRCF model can be effectively optimized based on the alternating direction method of multipliers, where each subproblem has the closed -from solution. Third, our tracker applies two kinds of CF models to estimate the location and scale respectively. The location CF model exploits ensembles of shallow and deep features to determine the optimal position accurately. The scale CF model works on multi-scale shallow features to estimate the optimal scale efficiently. Extensive experiments on five recent benchmarks show that our tracker performs favorably against many state-of-the-art algorithms, with real-time performance of 28fps.
引用
收藏
页码:4665 / 4674
页数:10
相关论文
共 37 条
[1]  
[Anonymous], 2018, CVPR
[2]  
[Anonymous], 2015, ICCVW
[3]  
[Anonymous], 2016, ECCVW
[4]  
[Anonymous], 2015, ICCV
[5]  
[Anonymous], 2017, ICCV
[6]  
[Anonymous], 2016, ECCVW
[7]  
[Anonymous], 2017, CVPR
[8]  
[Anonymous], 2018, ECCV
[9]  
[Anonymous], 2018, ECCV
[10]  
[Anonymous], 2016, ECCV