Long-term Target Tracking Based on Template Updating and Redetection

Xu, Shuping; Li, Yinglong

doi:10.2478/ijanmc-2024-0035

Abstract

To address the issue of targets frequently disappearing and reappearing in long-term tracking scenarios due to occlusion and being out of view, we have developed a long-term target tracking algorithm based on template updating and redetection (LTUSiam). Firstly, on the basis of the basic tracker SiamRPN, a three-level cascade gated cycle unit is introduced to assess the state of the target and select the right time to adopt the template update network to adapt the update template information. Secondly, a re-detection algorithm based on template matching is proposed. The candidate region extraction module is utilized to adjust the target's position and size in the basic tracker, and the evaluation score sequence is used to judge the target loss to determine the tracking state of the next frame. Experiments show that LTUSiam achieves 28 frames per second on VOT2018_LT dataset, achieving good results in real-time tracking, and 0.644 performance on F-score, which has better robustness in handling the problem of target loss recurrence, and effectively improves the performance of long-term tracking.

References

S. M. Marvasti-Zadeh, L. Cheng, H. Ghanei-Yakhdan, and S. Kasaei, “Deep Learning for Visual Tracking: A Comprehensive Survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 5, pp. 3943–3968, 2022, doi: 10.1109/TITS.2020.3046478.
Open DOI Search in Google Scholar Back to article
Y. Zhang, T. Wang, K. Liu, B. Zhang, and L. Chen, “Recent advances of single-object tracking methods: Abrief survey,” Neurocomputing, vol. 455, pp. 1–11, 2021, doi:https://doi.org/10.1016/j.neucom.2021.05.011.
Search in Google Scholar Back to article
J. Zhang, J. Sun, J. Wang, and X.-G. Yue, “Visual object tracking based on residual network and cascaded correlation filters,” Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 8, pp. 8427–8440, Aug. 2021, doi: 10.1007/s12652-020-02572-0.
Open DOI Search in Google Scholar Back to article
F. Chen, X. Wang, Y. Zhao, S. Lv, and X. Niu, “Visual object tracking: A survey,” Computer Vision and Image Understanding, vol. 222, p. 103508, 2022, doi: https://doi.org/10.1016/j.cviu.2022.103508.
Search in Google Scholar Back to article
J. Chai, H. Zeng, A. Li, and E. W. T. Ngai, “Deep learning in computer vision: A critical review of emerging techniques and application scenarios,” Machine Learning with Applications, vol. 6, p. 100134, 2021, doi: https://doi.org/10.1016/j.mlwa.2021.100134.
Search in Google Scholar Back to article
K. Tong and Y. Wu, “Deep learning-based detection from the perspective of small or tiny objects: A survey,” Image and Vision Computing, vol. 123, p. 104471, 2022, doi: https://doi.org/10.1016/j.imavis.2022.104471.
Search in Google Scholar Back to article
Y. Zhang, L. Wang, D. Wang, J. Qi, and H. Lu, “Learning Regression and Verification Networks for Robust Long-term Tracking,” International Journal of Computer Vision, vol. 129, no. 9, pp. 2536–2547, Sep. 2021, doi: 10.1007/s11263-021-01487-3.
Open DOI Search in Google Scholar Back to article
E. Tian, Y. Lei, J. Sun, K. Zhou, B. Zhou, and H. Li, “The Segmentation Tracker With Mask-Guided Background Suppression Strategy,” IEEE Access, vol. 12, pp. 124032–124044, 2024, doi: 10.1109/ACCESS.2024.3451229.
Open DOI Search in Google Scholar Back to article
K. Dai, Y. Zhang, D. Wang, J. Li, H. Lu, and X. Yang, “High-Performance Long-Term Tracking With MetaUpdater,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2020.
Search in Google Scholar Back to article
L. Huang, X. Zhao, and K. Huang, “GlobalTrack: A Simple and Strong Baseline for Long-Term Tracking,” AAAI, vol. 34, no. 07, pp. 11037–11044, Apr. 2020, doi: 10.1609/aaai.v34i07.6758.
Open DOI Search in Google Scholar Back to article
H. Fan et al., “LaSOT: A High-quality Large-scale Single Object Tracking Benchmark,” International Journal of Computer Vision, vol. 129, no. 2, pp. 439–461, Feb. 2021, doi: 10.1007/s11263-020-01387-y.
Open DOI Search in Google Scholar Back to article
R. Faster, “Towards real-time object detection with region proposal networks,” Advances in neural information processing systems, vol. 9199, no. 10.5555, pp. 2969239–2969250, 2015.
Search in Google Scholar Back to article
L. Bertinetto, J. Valmadre, J. F. Henriques, A. Vedaldi, and P. H. S. Torr, “Fully-Convolutional Siamese Networks for Object Tracking,” in Computer Vision - ECCV 2016 Workshops, G. Hua and H. Jégou, Eds., Cham: Springer International Publishing, 2016, pp. 850–865.
Search in Google Scholar Back to article
B. Li et al., “Evolution of siamese visual tracking with very deep networks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019, pp. 15–20.
Search in Google Scholar Back to article
M. Zolfaghari, K. Singh, and T. Brox, “Eco: Efficient convolutional network for online video understanding,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 695–712.
Search in Google Scholar Back to article
A. Lukežič, L. Č. Zajc, T. Vojíř, J. Matas, and M. Kristan, “Now you see me: evaluating performance in long-term visual tracking,” arXiv preprint arXiv:1804.07056, 2018.
Search in Google Scholar Back to article
L. Leal-Taixé, A. Milan, I. Reid, S. Roth, K. M. Schindler, and M. Challenge, “Towards a benchmark for multi-target tracking,” arXiv preprint arXiv:1504.01942, vol. 34, 2015.
Search in Google Scholar Back to article

Long-term Target Tracking Based on Template Updating and Redetection

Abstract

Paradigm

My account