Residual attention mechanism for visual tracking

被引：0
|
作者：
Cheng L. [1 ]
Wang Y. [1 ]
Tian C. [1 ]
机构：
[1] School of Electronic Engineering, Xidian University, Xi'an
来源：
Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University | 2020年 / 47卷 / 06期
关键词：
Attention mechanism; Convolutional neural network; Object tracking; Residual network;
D O I：
10.19665/j.issn1001-2400.2020.06.021
中图分类号：
学科分类号：
摘要：
In recent years, with the development of training data and hardware, a large number of tracking algorithms based on deep learning have been proposed. Compared with the traditional tracking algorithm, tracking algorithms based on deep learning have a great developing potential. However, the traditional convolutional neural network structure cannot effectively perform its powerful feature learning and representation abilities in a tracking task. In this paper, an improved feature extraction network is proposed for video target tracking. Based on the traditional feature extraction network, an attention mechanism and a feature fusion strategy in the form of residual network are introduced. At the same time, a loss function based on the regional overlap rate is introduced in the training stage of the network model, which makes the algorithm produce a better positioning effect. Experimental results show that the improved algorithm can track the target accurately for a long time. Besides, the method has a generalization ability, which can be used for reference for other tracking algorithms based on deep learning. © 2020, The Editorial Board of Journal of Xidian University. All right reserved.
引用
收藏
页码：148 / 157and163
相关论文
共 29 条
  • [1] WANG Haijun, ZHANG Shengyan, Robust Object Tracking Via Adaptive Weight Convolutional Features, Journal of Xidian University, 46, 1, pp. 117-123, (2019)
  • [2] 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, (2015)
  • [3] DANELLJAN M, HAGER G, KHAN F S, Et al., Accurate Scale Estimation for Robust Visual Tracking, Proceedings of the 2014 British Machine Vision Conference, (2014)
  • [4] SONG Jianfeng, MIAO Qiguang, SHEN Meng, Et al., Algorithm for Tracking an Infrared Single Target Based on Correlation Filtering with Multi-feature Fusion, Journal of Xidian University, 46, 5, pp. 142-147, (2019)
  • [5] WANG Xinyuan, XIAO Song, LI Lei, Et al., Robust Target Tracking Algorithm Based on the ELM and Discriminative Correlation Filter, Journal of Xidian University, 46, 1, pp. 57-63, (2019)
  • [6] NAM H, HAN B., Learning Multi-domain Convolutional Neural Networks for Visual Tracking, Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 4293-4302, (2016)
  • [7] NAM H, BAEK M, HAN B., Modeling and Propagating CNNs in a Tree Structure for Visual Tracking
  • [8] HELD D, THRUN S, SAVARESE S., Learning to Track at 100 FPS with Deep Regression Networks, Lecture Notes in Computer Science: 9905, pp. 749-765, (2016)
  • [9] BERTINETTO L, VALMADRE J, HENRIQUES J F, Et al., Fully Convolutional Siamese Networks for Object Tracking, Lecture Notes in Computer Science: 9914, pp. 850-865, (2016)
  • [10] GUO Q, FENG W, ZHOU C, Et al., Learning Dynamic Siamese Network for Visual Object Tracking, Proceedings of the 2017 IEEE International Conference on Computer Vision, pp. 1781-1789, (2017)
123