Siamese network visual tracking algorithm based on second-order attention

被引：0
|
作者：
Hou Z. [1 ,2 ]
Chen M. [1 ,2 ]
Ma J. [1 ,2 ]
Guo F. [1 ,2 ]
Yu W. [3 ]
Ma S. [1 ,2 ]
机构：
[1] School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an
[2] Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an University of Posts and Telecommunications, Xi'an
[3] School of Information and Navigation, Air Force Engineering University, Xi'an
来源：
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics | 2024年 / 50卷 / 03期
基金：
中国国家自然科学基金;
关键词：
double branch response strategy; residual second-order pooling network; second-order spatial attention network; Siamese network; visual tracking;
D O I：
10.13700/j.bh.1001-5965.2022.0373
中图分类号：
学科分类号：
摘要：
To improve the feature expression ability and discriminative ability of the visual tracking algorithm based on Siamese network and obtain better tracking performance, a lightweight Siamese network visual tracking algorithm based on second-order attention is proposed. Firstly, to obtain deep features of the object, the lightweight VGG-Net is used as the backbone of the Siamese network.Secondly, the residual second-order pooling network and the second-order spatial attention network are used in parallel at the end of the Siamese network to obtain the second-order attention features with channel correlation and the second-order attention features with spatial correlation.Finally, visual tracking is achieved through a double branch response strategy using the residual second-order channel attention features and the second-order spatial attention features. The proposed algorithm is trained end-to-end with the GOT-10k dataset and validated on the datasets OTB100 and VOT2018.The experimental results show that the tracking performance of the proposed algorithm has been significantly improved. Compared with the baseline algorithm SiamFC, on dataset OTB100, the precision and the success are increased by 0.100 and 0.096, respectively; on dataset VOT2018, the expected average overlap (EAO) increased by 0.077, tracking speed reached 48 frame/s. © 2024 Beijing University of Aeronautics and Astronautics (BUAA). All rights reserved.
引用
收藏
页码：739 / 747
页数：8
相关论文
共 29 条
  • [1] MARVASTI-ZADEH S M, CHENG L, GHANEI-YAKHDAN H., Deep learning for visual tracking: A comprehensive survey, IEEE Transactions on Intelligent Transportation Systems, 23, 5, pp. 3943-3968, (2022)
  • [2] BAI L, ZHANG H L, WANG C., Target tracking algorithm based on efficient attention and context awareness, Journal of Beijing University of Aeronautics and Astronautics, 48, 7, pp. 1222-1232, (2022)
  • [3] LI X, ZHA Y F, ZHANG T Z, Et al., A survey of visual object tracking algorithms based on deep learning, Journal of Image and Graphics, 24, 12, pp. 2057-2080, (2019)
  • [4] PU L, LI H L, HOU Z Q, Et al., Siamese network tracking based on high level semantic embedding, Journal of Beijing University of Aeronautics and Astronautics, 49, 4, pp. 792-803, (2023)
  • [5] ZHANG C Y, HOU Z Q, PU L, Et al., Siamese network visual tracking algorithm based on online learning, Opto-Electronic Engineering, 48, 4, pp. 4-14, (2021)
  • [6] BERTINETTO L, VALMADRE J, HENRIQUES J F., Fully-convolutional Siamese networks for object tracking, Proceedings of the European Conference on Computer Vision, pp. 850-865, (2016)
  • [7] LI B, YAN J, WU W., High performance visual tracking with Siamese region proposal network, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971-8980, (2018)
  • [8] ZHU Z, WANG Q, LI B., Distractor-aware Siamese networks for visual object tracking, Proceedings of the European Conference on Computer Vision, pp. 101-117, (2018)
  • [9] KRIZHEVSKY A, SUTSKEVER I, HINTON G E., ImageNet classification with deep convolutional neural networks, Communications of the ACM, 60, 6, pp. 84-90, (2017)
  • [10] WANG Q, ZHANG L, WU B., What deep CNNs benefit from global covariance pooling: An optimization perspective, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10771-10780, (2020)
123