Share Email Print
cover

Proceedings Paper • new

Fine scale estimation for correlation filter tracking
Author(s): Yanchuan Wang; Hongtao Yu; Shaomei Li; Chao Gao; Hongxin Zhi; Cha Zheng; Qian Xu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Focusing on the issue that Correlation Filter Trackers has poor performance in scale variations, a fine scale estimation approach is proposed. Firstly, we train a scale correlation filter using the target initial state. Secondly, the target is segmented according to its shape and then two subgraph correlation filters are respectively established. During tracking, we judge the trend of scale changes by the relative position changes of the subgraphs and the weights of the scale samples are offset. In this way, we obtain the coarse scale estimation of the target. Finally, we use Newton method to accurately estimate the scale of the target. Experiments show that the algorithm achieves more accurate scale estimation and effectively improves the tracking success rate.

Paper Details

Date Published: 26 July 2018
PDF: 7 pages
Proc. SPIE 10828, Third International Workshop on Pattern Recognition, 1082816 (26 July 2018); doi: 10.1117/12.2501792
Show Author Affiliations
Yanchuan Wang, National Digital Switching System Engineering and Technological Research Ctr. (China)
Hongtao Yu, National Digital Switching System Engineering and Technological Research Ctr. (China)
Shaomei Li, National Digital Switching System Engineering and Technological Research Ctr. (China)
Chao Gao, National Digital Switching System Engineering and Technological Research Ctr. (China)
Hongxin Zhi, National Digital Switching System Engineering and Technological Research Ctr. (China)
Cha Zheng, National Digital Switching System Engineering and Technological Research Ctr. (China)
Qian Xu, National Digital Switching System Engineering and Technological Research Ctr. (China)


Published in SPIE Proceedings Vol. 10828:
Third International Workshop on Pattern Recognition
Xudong Jiang; Zhenxiang Chen; Guojian Chen, Editor(s)

© SPIE. Terms of Use
Back to Top