1
|
Peng Y, Gao J, Liu C, Li X, Fan B, Chen J, Luo J, Xie S, Pu H. Soft labeling with quasi-Gaussian structure for training samples of deep classification trackers. INT J ADV ROBOT SYST 2020. [DOI: 10.1177/1729881420915025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
Deep classification tracking aims at classifying the candidate samples into target or background by a classifier generally trained with a binary label. However, the binary label merely distinguishes samples of different classes, while inadvertently ignoring the distinction among the samples belonging to the same class, which weakens the classification and locating ability. To cope with this problem, this article proposes a soft labeling with quasi-Gaussian structure instead of the binary labeling, which distinguishes the samples belonging to different classes and the same class simultaneously. Like as the binary label, the signs of labels for target and background samples are set to be plus and minus respectively to distinguish samples of different classes. Further, to exploit the difference among samples in the same class, the label values of samples in the same class are designed as a monotonically decreasing quasi-Gaussian function about Intersection over Union. Therefore, the corresponding response function is a two-piecewise monotonically increasing quasi-Gaussian combination function about Intersection over Union. Due to such response function, deep classification tracking trained with this proposed soft labeling achieves better classification and location performance. To validate this, the proposed soft labeling is integrated into the pipeline of the deep classification tracker SiamFC. Experimental results on OTB-2015 and VOT benchmark show that our variant achieves significant improvement to the baseline tracker while maintaining real-time tracking speed and acquires comparable accuracy as recent state-of-the-art trackers.
Collapse
Affiliation(s)
- Yan Peng
- Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
| | - Jiantao Gao
- Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
| | - Chang Liu
- Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
| | - Xiaomao Li
- Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
| | - Baojie Fan
- Automation College, Nanjing University of Posts and Telecommunications, Nanjing, China
| | - Jiahong Chen
- Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
| | - Jun Luo
- Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
| | - Shaorong Xie
- Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
| | - Huayan Pu
- Research Institute of USV Engineering, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
| |
Collapse
|