Learning Attentional Regularized Correlation Filter for Visual Tracking

被引：0

作者：

Qiu Z.-L. ^{[1
]}

Zha Y.-F. ^{[1
,2
]}

Wu M. ^{[3
]}

Wang Q. ^{[3
]}

机构：

[1] Aeronautics Engineering College, Air Force Engineering University, Xi'an, 710038, Shaanxi

[2] School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, Shaanxi

[3] Unit 95972 of the PLA, Beijing

来源：

Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2020年 / 48卷 / 09期

关键词：

Attention mechanism; Correlation filter; Machine learning; Regularization; Single target; Visual tracking;

D O I：

10.3969/j.issn.0372-2112.2020.09.014

中图分类号：

学科分类号：

摘要：

Boundary effect is an important factor which restricts the performance of correlation filter. At present, most methods simply use the prior knowledge, such as inverse Gaussian distribution, preset masks, etc., or segment the foreground target to constrain solving as the regularization term, which do not consider characteristics of the target in the spatial and temporal domain. To address this problem, this paper proposes a learning attention regularized correlation filter for visual tracking. The method uses the attention mechanism to learn the specific spatial weight of the target, which can adapt to the variations of target in the spatial domain by considering the spatial distribution characteristics of the target. At the same time, this paper uses the continuity of the target in the temporal domain. The filter is indirectly adjusted by constraining the attention weight matrix. Finally, the alternating direction method of multipliers (ADMM) is employed to iteratively optimize the model. We conduct extensive experiments on the proposed method in the standard tracking database. The results show that the proposed algorithm can track the target in real time, and has a certain improvement in precision and success rate. © 2020, Chinese Institute of Electronics. All right reserved.

引用

页码：1762 / 1768

页数：6

共 15 条

[1] Sun Hang, Li Jing, Du Bo, Et al., Correlation filter target tracking based on multi-stage learning, Acta Electronica Sinica, 45, 10, pp. 2337-2342, (2017)
[2] Fan Shun-yi, Guan Hua, Hou Zhi-qiang, Et al., Robust visual tracking based on multi-epitopic characterization sub-model updating, Acta Electronica Sinica, 46, pp. 440-446, (2018)
[3] Henriques J F, Caseiro R, Martins P, Et al., High-speed tracking with kernelized correlation filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 3, pp. 583-596, (2014)
[4] Wu Y, Lim J, Yang M H., Object tracking benchmark, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 9, pp. 1834-1848, (2015)
[5] Kristan M, Leonardis A, Matas J, Et al., The visual object tracking vot2017 challenge results, Proceedings of the International Conference on Computer Vision, pp. 1949-1972, (2017)
[6] Danelljan M, Hager G, Khan F S, Et al., Learning spatially regularized correlation filters for visual tracking, Proceedings of the International Conference on Computer Vision, pp. 4310-4318, (2015)
[7] Kiani Galoogahi H, Fagg A, Lucey S., Learning background-aware correlation filters for visual tracking, Proceedings of the International Conference on Computer Vision, pp. 1135-1143, (2017)
[8] Lukezic A, Vojir T, Cehovin Zajc L, Et al., Discriminative correlation filter with channel and spatial reliability, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6309-6318, (2017)
[9] Ghadimi E, Teixeira A, Shames I, Et al., Optimal parameter selection for the alternating direction method of multipliers (ADMM): quadratic problems, IEEE Transactions on Automatic Control, 60, 3, pp. 644-658, (2014)
[10] Li F, Tian C, Zuo W, Et al., Learning spatial-temporal regularized correlation filters for visual tracking, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4904-4913, (2018)

← 1 2 →