Object tracking method based on loU-constrained Siamese network

被引：0
|
作者：
Zhou L. [1 ,2 ,3 ]
Liu J. [1 ,3 ]
Li W. [2 ,3 ]
Lei B. [4 ]
He Y. [1 ,3 ]
Wang Y. [1 ]
机构：
[1] School of Software Engineering, Chongqing University of Posts and Telecommunications, Chongqing
[2] School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing
[3] Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing
[4] Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University, Yichang
来源：
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics | 2022年 / 48卷 / 08期
关键词：
deep learning; dynamic threshold; intersection over union (IoU)-constrained; object tracking; Siamese network;
D O I：
10.13700/j.bh.1001-5965.2021.0533
中图分类号：
学科分类号：
摘要：
The tracking method based on the Siamese network trains the tracking model offline. Therefore, it maintains a good balance between tracking accuracy and speed, which attracts the interest of a growing number of researchers recently. The existing Siamese network object tracking method uses a fixed threshold to select positive and negative training samples, which is easy to cause the problem of missing training samples, and such methods have low correlation between the classification branch and the regression branch during training, which is not conducive to training a high-precision tracking model. To this end, an object tracking method based on intersection over union (IoU)-constrained Siamese network is proposed. By using a dynamic threshold strategy, the thresholds of positive and negative training samples are dynamically adjusted according to the relevant statistical characteristics of the predefined anchor boxes and the real boxes. Thereby improving the tracking accuracy. In addition, the proposed method uses the IoU quality assessment branch to replace the classification branch, and reflects the position of the target through the IoU between the anchor box and the target ground-truth frame, which improves the tracking accuracy and reduces the amount of model parameters. The proposed object tracking method based on the IoU-constrained Siamese network has been compared and tested on four datasets; VOT2016, OTB-100, VOT2019, and UAV123. Ideal results have been achieved in these datasets. The tracking accuracy of the proposed method in this paper is 0. 017 higher than SiamRPN on the VOT2016 dataset. And with a real-time running speed at 220 frame/s, the expected average overlap rate is 0. 463, which is only 0. 001 worse than SiamRPN + +. © 2022 Beijing University of Aeronautics and Astronautics (BUAA). All rights reserved.
引用
收藏
页码：1390 / 1398
页数：8
相关论文
共 42 条
  • [1] ZHOU Q L, ZHANG W J, ZHAO L P, Et al., Cross-modal object tracking algorithm based on pedestrian attribute [J], Journal of Beijing University of Aeronautics and Astronautics, 46, 9, pp. 1635-1642, (2020)
  • [2] LUO Y, XIAO H, OU J X., Research on target tracking technology based on deep learning[J], Semiconductor Optoelectronics, 41, 6, (2020)
  • [3] ZHANG S F, CHI C, YAO Y Q, Et al., Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9759-9768, (2020)
  • [4] XU Y D, WANG Z Y, LI Z X, Et al., SiamFC + +: Towards robust and accurate visual tracking with target estimation guidelines [ C], Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12549-12556, (2020)
  • [5] LI B, YAN J J, WU W, Et al., High performance visual tracking with Siamese region proposal network [ C ], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971-8980, (2018)
  • [6] TAO R, GAVVES E, SMEULDERS A W M., Siamese instance search for tracking [ C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1420-1429, (2016)
  • [7] BERTINETTO L, VALMADRE J, HENRIQUES J F, Et al., Fully-convolutional Siamese networks for object tracking, European Conference on Computer Vision, pp. 850-865, (2016)
  • [8] DENG J, SU H, Et al., ImageNet large scale visual recognition challenge [ J ], International Journal of Computer Vision, 115, 3, pp. 211-252, (2015)
  • [9] VALMADRE J, BERTINETTO L, HENRIQUES J, Et al., End-to-end representation learning for correlation filter based tracking, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2805-2813, (2017)
  • [10] WANG Q, TENG Z, XING J L, Et al., Learning attentions: Residual attentional Siamese network for high performance online visual tracking [ C ], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4854-4863, (2018)
12345