Object Tracking Based on Adaptive Multi-Template Fusing
Authors: 
Ziliang Guo, Zihao Li, Xiwen Zhang, Xingqi Fang, Yi Tian, Xiaowei Zhang, Yu QiaoAuthors Info & Claims
Ziliang Guo, Zihao Li, Xiwen Zhang, Xingqi Fang, Yi Tian, Xiaowei Zhang, Yu QiaoAuthors Info & ClaimsArticle No.: 6, Pages 1 - 6
Abstract
Target lost and robustness to occlusion scenarios hinder real-world applications of current object tracking methods. In this paper, we focus on reducing the frames of target lost in the single object tracking task. We propose a multi-template object tracking framework which incorporates occlusion detection. Firstly, the multi-template design memorizes long-term target appearance, and adaptively fuses into a unified template based on short-term similarity knowledge. Secondly, the evaluated occlusion severity guides the template updating. As a result, the insensitivity to the learning rate is achieved on VOT2016 and VOT2018. The significant decrease in frames of lost target further highlights the superiority of our approach.
References
[1]
Zanzhou Bai, Zihao Li, and 2022. Training Efficient Siamese Network with Probability Label for Object Tracking. In 2022 5th International Conference on Data Science and Information Technology (DSIT). IEEE, 01–06.
[2]
Luca Bertinetto, Jack Valmadre, Joao F Henriques, and 2016. Fully-convolutional siamese networks for object tracking. In Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14. Springer, 850–865.
[3]
David S Bolme, J Ross Beveridge, Bruce A Draper, and Yui Man Lui. 2010. Visual object tracking using adaptive correlation filters. In 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 2544–2550.
[4]
Xin Chen and 2021. Transformer tracking. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 8126–8135.
[5]
Davide Chicco. 2021. Siamese neural networks: An overview. Artificial neural networks (2021), 73–94.
[6]
Yutao Cui, Cheng Jiang, and 2022. Mixformer: End-to-end tracking with iterative mixed attention. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13608–13618.
[7]
Martin Danelljan, Gustav Hager, Fahad Shahbaz Khan, and Michael Felsberg. 2015. Learning spatially regularized correlation filters for visual tracking. In Proceedings of the IEEE international conference on computer vision. 4310–4318.
[8]
Kunqi Gu and 2016. Correlation filter tracking via bootstrap learning. In 2016 IEEE International Conference on Image Processing (ICIP). IEEE, 459–463.
[9]
Kunqi Gu, Mingna Liu, Tao Zhou, Fanghui Liu, and 2016. Patch-based object tracking via locality-constrained linear coding. In 2016 35th Chinese Control Conference (CCC). IEEE, 7015–7020.
[10]
Yueyang Gu, Xiaoguang Niu, and Yu Qiao. 2019. Robust visual tracking via adaptive occlusion detection. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2242–2246.
[11]
Yueyang Gu, Yu Qiao, and 2020. Robust visual tracking with context-based active occlusion recognition. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1878–1882.
[12]
SJ Hadfield and 2016. The visual object tracking VOT2016 challenge results. Lecture Notes in Computer Science 9914 (2016), 777–823.
[13]
João F Henriques, Rui Caseiro, Pedro Martins, and Jorge Batista. 2014. High-speed tracking with kernelized correlation filters. IEEE transactions on pattern analysis and machine intelligence 37, 3 (2014), 583–596.
[14]
Xiuhua Hu and 2022. Transformer feature enhancement network with template update for object tracking. Sensors 22, 14 (2022), 5219.
[15]
Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, and Junjie Yan. 2019. Siamrpn++: Evolution of siamese visual tracking with very deep networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 4282–4291.
[16]
Bi Li, Wenxuan Xie, Wenjun Zeng, and Wenyu Liu. 2019. Learning to update for object tracking with recurrent meta-learner. IEEE Transactions on Image Processing 28, 7 (2019), 3624–3635.
[17]
Bo Li, Junjie Yan, Wei Wu, Zheng Zhu, and Xiaolin Hu. 2018. High performance visual tracking with siamese region proposal network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 8971–8980.
[18]
Peixia Li, Dong Wang, and 2018. Deep visual tracking: Review and experimental comparison. Pattern Recognition 76 (2018), 323–338.
[19]
Yang Li and Jianke Zhu. 2015. A scale adaptive kernel correlation filter tracker with feature integration. In Computer Vision-ECCV 2014 Workshops: Zurich, Switzerland, September 6-7 and 12, 2014, Proceedings, Part II 13. Springer, 254–265.
[20]
Liting Lin, Heng Fan, Zhipeng Zhang, Yong Xu, and Haibin Ling. 2022. Swintrack: A simple and strong baseline for transformer tracking. Advances in Neural Information Processing Systems 35 (2022), 16743–16754.
[21]
Alan Lukežič and 2018. Now you see me: evaluating performance in long-term visual tracking. arXiv preprint arXiv:1804.07056 (2018).
[22]
L. Matthews and 2004. The template update problem. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 6 (2004), 810–815.
[23]
Xiaoguang Niu and Yu Qiao. 2017. Context-based occlusion detection for robust visual tracking. In 2017 IEEE International Conference on Image Processing (ICIP). IEEE, 3655–3659.
[24]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).
[25]
Ning Wang, Wengang Zhou, Jie Wang, and Houqiang Li. 2021. Transformer meets tracker: Exploiting temporal context for robust visual tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1571–1580.
[26]
Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, and Philip HS Torr. 2019. Fast online object tracking and segmentation: A unifying approach. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition. 1328–1338.
[27]
Yinda Xu, Zeyu Wang, Zuoxin Li, Ye Yuan, and Gang Yu. 2020. Siamfc++: Towards robust and accurate visual tracking with target estimation guidelines. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 12549–12556.
[28]
Lichao Zhang, Abel Gonzalez-Garcia, Joost van de Weijer, Martin Danelljan, and Fahad Shahbaz Khan. 2019. Learning the model update for siamese trackers. In Proceedings of the IEEE/CVF international conference on computer vision. 4010–4019.
[29]
Fei Zhao and 2020. Siamese regression tracking with reinforced template updating. IEEE Transactions on Image Processing 30 (2020), 628–640.
[30]
Zheng Zhu, Qiang Wang, Bo Li, Wei Wu, Junjie Yan, and Weiming Hu. 2018. Distractor-aware siamese networks for visual object tracking. In Proceedings of the European conference on computer vision (ECCV). 101–117.
Recommendations
Robust object tracking via multi-cue fusion
A long-term object tracking method based on calibrated binocular cameras by fusing information of the two channels and binocular geometry constraints is proposed.The stereo filter which is built based on the epipolar geometry of the binocular cameras is ...
Adaptive Evolutionary Particle Filter Based Object Tracking with Occlusion Handling
ICNC '09: Proceedings of the 2009 Fifth International Conference on Natural Computation - Volume 05Fast and robust object tracking with occlusion handling is a challenging task. Particle filtering has proven very successful for non-linear and non-Gaussian estimation problems. The paper presents a method for occlusion detection for object tracking ...
Occlusion detection and recovery in video object tracking based on adaptive particle filters
CCDC'09: Proceedings of the 21st annual international conference on Chinese Control and Decision ConferenceOcclusion detection and recovery is a challenging task in robust real-time tracking of non-rigid objects. Particle filtering has proven very successful for non-linear and non-Gaussian estimation problems. The paper presents a method for occlusion ...
Comments
Information & Contributors
Information
Published In
April 2024
381 pages
ISBN:9798400716393
DOI:10.1145/3661725
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 20 June 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CMLDS 2024
CMLDS 2024: 2024 International Conference on Computing, Machine Learning and Data Science
April 12 - 14, 2024
Singapore, Singapore
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 23Total Downloads
- Downloads (Last 12 months)23
- Downloads (Last 6 weeks)2
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format