Learning Unsupervised Cross-Domain Model for TIR Target Tracking
Abstract
:1. Introduction
- We propose an unsupervised cross-domain model for the TIR tracking task.
- The cross-domain model could transfer the convolutional feature extraction network trained in the source RGB domain to the target TIR domain for the target feature extraction, which can improve the poor representation of the trained convolutional feature extraction network effectively due to insufficient training samples in the target TIR domain.
- To make the trained convolutional feature extraction network have a strong target representation capability, an unsupervised learning method is adopted to generate pseudo-labels for the unlabeled training samples in the source RGB domain for the convolutional feature extraction network training.
2. Related Works
3. The Proposed UCDT Tracker
3.1. Deep Correlation Tracking Framework
3.2. Cross-Domain Model
3.3. Unsupervised Pseudo-Label Generation
4. Experiments
4.1. Implementation Details
4.2. Experiments on PTB-TIR Benchmark
4.3. Experiments on LSOTB-TIR Benchmark
4.4. Qualitative Comparison
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Hou, S.; Wang, T.; Qiao, D.; Xu, D.J.; Wang, Y.; Feng, X.; Khan, W.A.; Ruan, J. Temporal-Spatial Fuzzy Deep Neural Network for the Grazing Behavior Recognition of Herded Sheep in Triaxial Accelerometer Cyber-Physical Systems. In IEEE Transactions on Fuzzy Systems; IEEE: New York, NY, USA, 2024; pp. 1–12. [Google Scholar]
- Wang, Y.; Khan, W.A.; Chung, S.H. Few-Shot Defect Detection of Catheter Products via Enlarged Scale Feature Pyramid and Contrastive Proposal Memory Bank. In IEEE Transactions on Industrial Informatics; IEEE: New York, NY, USA, 2024; pp. 1–11. [Google Scholar]
- Li, H.; Wang, X.; Shen, F.; Li, Y.; Porikli, F.; Wang, M. Real-time deep tracking via corrective domain adaptation. IEEE Trans. Circ. Syst. Video Technol. 2019, 29, 2600–2612. [Google Scholar] [CrossRef]
- Ye, J.; Fu, C.; Zheng, G.; Paudel, D.P.; Chen, G. Unsupervised domain adaptation for nighttime aerial tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 19–20 June 2022; pp. 8896–8905. [Google Scholar]
- Chen, Y.; Jiang, J.; Lei, R.; Bekiroglu, Y.; Chen, F.; Li, M. GraspAda: Deep grasp adaptation through domain transfer. In Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK, 29 May–2 June 2023; IEEE: New York, NY, USA, 2023; pp. 10268–10274. [Google Scholar]
- Zhao, L.; Ouyang, E.; Tang, J.; Li, B.; Wu, J.; Zhang, G.; Hu, W. Domain transfer and difference-aware band weighting for object tracking in hyperspectral videos. Int. J. Remote Sens. 2023, 44, 1115–1131. [Google Scholar] [CrossRef]
- Kuppusami Sakthivel, S.S.; Moorthy, S.; Arthanari, S.; Jeong, J.H.; Joo, Y.H. Learning a context-aware environmental residual correlation filter via deep convolution features for visual object tracking. Mathematics 2024, 12, 2279. [Google Scholar] [CrossRef]
- He, L.; Xu, Y.; Chen, Y.; Wen, J. Recent advance on mean shift tracking: A survey. Int. J. Image Graph. 2013, 13, 1350012. [Google Scholar] [CrossRef]
- Henriques, J.F.; Caseiro, R.; Martins, P.; Batista, J. High-Speed Tracking with Kernelized Correlation Filters. IEEE Trans. Pattern Anal. Mach. Intell. 2014, 37, 583–596. [Google Scholar] [CrossRef]
- Qi, Y.; Zhang, S.; Qin, L.; Yao, H.; Huang, Q.; Lim, J.; Yang, M.H. Hedged Deep Tracking. In Proceedings of the CVPR, Las Vegas, NV, USA, 27–30 June 2016; pp. 4303–4311. [Google Scholar]
- Husna Fauzi, N.I.; Musa, Z.; Hujainah, F. Feature-Based Object Detection and Tracking: A Systematic Literature Review. Int. J. Image Graph. 2024, 24, 2450037. [Google Scholar] [CrossRef]
- Li, D.; Chai, H.; Wei, Q.; Zhang, Y.; Xiao, Y. PACR: Pixel Attention in Classification and Regression for Visual Object Tracking. Mathematics 2023, 11, 1406. [Google Scholar] [CrossRef]
- Jiang, R.; Wang, Q.; Shi, S.; Mou, X.; Chen, S. Flow-assisted visual tracking using event cameras. CAAI Trans. Intell. Technol. 2021, 6, 192–202. [Google Scholar] [CrossRef]
- Kiani Galoogahi, H.; Fagg, A.; Lucey, S. Learning Background-Aware Correlation Filters for Visual Tracking. In Proceedings of the ICCV, Venice, Italy, 22–29 October 2017; pp. 1135–1143. [Google Scholar]
- Liu, L.; Feng, T.; Fu, Y.; Shen, C.; Hu, Z.; Qin, M.; Bai, X.; Zhao, S. Learning Adaptive Spatial Regularization and Temporal-Aware Correlation Filters for Visual Object Tracking. Mathematics 2022, 10, 4320. [Google Scholar] [CrossRef]
- Danelljan, M.; Hager, G.; Shahbaz Khan, F.; Felsberg, M. Learning Spatially Regularized Correlation Filters for Visual Tracking. In Proceedings of the ICCV, Santiago, Chile, 7–13 December 2015; pp. 4310–4318. [Google Scholar]
- Liu, B.; Chang, X.; Yuan, D.; Yang, Y. HCDC-SRCF tracker: Learning an adaptively multi-feature fuse tracker in spatial regularized correlation filters framework. Knowl.-Based Syst. 2022, 238, 107913. [Google Scholar] [CrossRef]
- Song, Y.; Ma, C.; Gong, L.; Zhang, J.; Lau, R.W.; Yang, M.H. CREST: Convolutional residual learning for visual tracking. In Proceedings of the ICCV, Venice, Italy, 22–29 October 2017; pp. 2574–2583. [Google Scholar]
- Li, D.; Zhang, Y.; Chen, M.; Chai, H. Attention and Pixel Matching in RGB-T Object Tracking. Mathematics 2023, 11, 1646. [Google Scholar] [CrossRef]
- Algabri, R.; Choi, M.T. Robust person following under severe indoor illumination changes for mobile robots: Online color-based identification update. In Proceedings of the 2021 21st International Conference on Control, Automation and Systems, Jeju, Republic of Korea, 12–15 October 2021; IEEE: New York, NY, USA, 2021; pp. 1000–1005. [Google Scholar]
- Yuan, D.; Shu, X.; Liu, Q.; He, Z. Structural target-aware model for thermal infrared tracking. Neurocomputing 2022, 491, 44–56. [Google Scholar] [CrossRef]
- Li, X.; Liu, Q.; Fan, N.; He, Z.; Wang, H. Hierarchical spatial-aware siamese network for thermal infrared object tracking. Knowl.-Based Syst. 2019, 166, 71–81. [Google Scholar] [CrossRef]
- Zhu, P.; Zheng, J.; Du, D.; Wen, L.; Sun, Y.; Hu, Q. Multi-drone-based single object tracking with agent sharing network. IEEE Trans. Circ. Syst. Video Technol. 2021, 31, 4058–4070. [Google Scholar] [CrossRef]
- Bertinetto, L.; Valmadre, J.; Henriques, J.F.; Vedaldi, A.; Torr, P.H. Fully-Convolutional Siamese Networks for Object Tracking. In Proceedings of the ECCV, Amsterdam, The Netherlands, 11–14 October 2016; pp. 850–865. [Google Scholar]
- Zhao, Y.; Zhang, J.; Duan, R.; Li, F.; Zhang, H. Lightweight target-aware attention learning network-based target tracking method. Mathematics 2022, 10, 2299. [Google Scholar] [CrossRef]
- Wang, Q.; Zhang, L.; Bertinetto, L.; Hu, W.; Torr, P.H. Fast online object tracking and segmentation: A unifying approach. In Proceedings of the CVPR, Long Beach, CA, USA, 15–20 June 2019; pp. 1328–1338. [Google Scholar]
- Guo, Q.; Feng, W.; Zhou, C.; Huang, R.; Wan, L.; Wang, S. Learning dynamic siamese network for visual object tracking. In Proceedings of the ICCV, Venice, Italy, 27–29 October 2017; pp. 1763–1771. [Google Scholar]
- Liu, Q.; Li, X.; He, Z.; Fan, N.; Yuan, D.; Liu, W.; Liang, Y. Multi-task driven feature models for thermal infrared tracking. In Proceedings of the AAAI, New York, NY, USA, 7–12 February 2020; Volume 34, pp. 11604–11611. [Google Scholar]
- Yuan, D.; Shu, X.; Liu, Q.; He, Z. Aligned Spatial-Temporal Memory Network for Thermal Infrared Target Tracking. IEEE Trans. Circ. Syst. II Express Briefs 2023, 70, 1224–1228. [Google Scholar] [CrossRef]
- Liu, Q.; Li, X.; Yuan, D.; Yang, C.; Chang, X.; He, Z. LSOTB-TIR: A large-scale high-diversity thermal infrared single object tracking benchmark. IEEE Trans. Neural Netw. Learn. Syst. 2024, 35, 9844–9857. [Google Scholar] [CrossRef]
- Yuan, D.; Zhang, H.; Shu, X.; Liu, Q.; Chang, X.; He, Z.; Shi, G. Thermal infrared target tracking: A comprehensive review. IEEE Trans. Instrum. Meas. 2024, 73, 5000419. [Google Scholar] [CrossRef]
- Lai, S.; Liu, C.; Wang, D.; Lu, H. Refocus the Attention for Parameter-Efficient Thermal Infrared Object Tracking. In IEEE Transactions on Neural Networks and Learning Systems; IEEE: New York, NY, USA, 2024. [Google Scholar]
- Yang, C.; Liu, Q.; Li, G.; Pan, H.; He, Z. Learning diverse fine-grained features for thermal infrared tracking. Expert Syst. Appl. 2024, 238, 121577. [Google Scholar] [CrossRef]
- Gao, P.; Li, S.M.; Gao, F.; Wang, F.; Yuan, R.Y.; Fujita, H. In defense and revival of Bayesian filtering for thermal infrared object tracking. Knowl.-Based Syst. 2024, 293, 111665. [Google Scholar] [CrossRef]
- Liu, Q.; He, Z.; Li, X.; Zheng, Y. PTB-TIR: A thermal infrared pedestrian tracking benchmark. IEEE Trans. Multimed. 2019, 22, 666–675. [Google Scholar] [CrossRef]
- Liu, Q.; Li, X.; He, Z.; Li, C.; Li, J.; Zhou, Z.; Yuan, D.; Li, J.; Yang, K.; Fan, N.; et al. LSOTB-TIR: A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark. In Proceedings of the ACM MM, Seattle, WA, USA, 12–16 October 2020; pp. 3847–3856. [Google Scholar]
- Khan, W.A.; Chung, S.H.; Awan, M.U.; Wen, X. Machine learning facilitated business intelligence (Part I) Neural networks learning algorithms and applications. Ind. Manag. Data Syst. 2020, 120, 164–195. [Google Scholar] [CrossRef]
- Kim, W.; Kanezaki, A.; Tanaka, M. Unsupervised learning of image segmentation based on differentiable feature clustering. IEEE Trans. Image Process. 2020, 29, 8055–8068. [Google Scholar] [CrossRef]
- Ma, C.; Huang, J.B.; Yang, X.; Yang, M.H. Hierarchical convolutional features for visual tracking. In Proceedings of the ICCV, Santiago, Chile, 7–13 December 2015; pp. 3074–3082. [Google Scholar]
- Li, X.; Ma, C.; Wu, B.; He, Z.; Yang, M.H. Target-aware deep tracking. In Proceedings of the CVPR, Long Beach, CA, USA, 15–19 June 2019; pp. 1369–1378. [Google Scholar]
- Gundogdu, E.; Koc, A.; Solmaz, B.; Hammoud, R.I.; Aydin Alatan, A. Evaluation of feature channels for correlation-filter-based visual object tracking in infrared spectrum. In Proceedings of the CVPRW, Las Vegas, NV, USA, 27–30 June 2016; pp. 24–32. [Google Scholar]
- Liu, Q.; Lu, X.; He, Z.; Zhang, C.; Chen, W.S. Deep convolutional neural networks for thermal infrared object tracking. Knowl.-Based Syst. 2017, 134, 189–198. [Google Scholar] [CrossRef]
- Yuan, D.; Chang, X.; Liu, Q.; Yang, Y.; Wang, D.; Shu, M.; He, Z.; Shi, G. Active Learning for Deep Visual Tracking. In IEEE Transactions on Neural Networks and Learning Systems; IEEE: New York, NY, USA, 2023; pp. 1–13. [Google Scholar]
- Xie, F.; Wang, Z.; Ma, C. DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 17–21 June 2024; pp. 19113–19124. [Google Scholar]
- Cai, W.; Liu, Q.; Wang, Y. HIPTrack: Visual Tracking with Historical Prompts. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 17–21 June 2024; pp. 19258–19267. [Google Scholar]
- Li, X.; Ding, H.; Yuan, H.; Zhang, W.; Pang, J.; Cheng, G.; Chen, K.; Liu, Z.; Loy, C.C. Transformer-based visual segmentation: A survey. In IEEE Transactions on Pattern Analysis and Machine Intelligence; IEEE: New York, NY, USA, 2024. [Google Scholar]
- Fu, C.; Lu, K.; Zheng, G.; Ye, J.; Cao, Z.; Li, B.; Lu, G. Siamese object tracking for unmanned aerial vehicle: A review and comprehensive analysis. Artif. Intell. Rev. 2023, 56, 1417–1477. [Google Scholar] [CrossRef]
- Zhang, H.; Yuan, D.; Shu, X.; Li, Z.; Liu, Q.; Chang, X.; He, Z.; Shi, G. A Comprehensive Review of RGBT Tracking. IEEE Trans. Instrum. Meas. 2024, 73, 5027223. [Google Scholar] [CrossRef]
- Huang, B.; Dou, Z.; Chen, J.; Li, J.; Shen, N.; Wang, Y.; Xu, T. Searching Region-Free and Template-Free Siamese Network for Tracking Drones in TIR Videos. In IEEE Transactions on Geoscience and Remote Sensing; IEEE: New York, NY, USA, 2023. [Google Scholar]
- Huang, Y.; He, Y.; Lu, R.; Li, X.; Yang, X. Thermal infrared object tracking via unsupervised deep correlation filters. Digit. Signal Process. 2022, 123, 103432. [Google Scholar] [CrossRef]
- Zha, Y.; Sun, J.; Zhang, P.; Zhang, L.; Gonzalez-Garcia, A.; Huang, W. Self-supervised cross-modal distillation for thermal infrared tracking. IEEE MultiMed. 2022, 29, 80–96. [Google Scholar] [CrossRef]
- Shu, X.; Yang, Y.; Wu, B. A neighbor level set framework minimized with the split Bregman method for medical image segmentation. Signal Process. 2021, 189, 108293. [Google Scholar] [CrossRef]
- Shu, X.; Yang, Y.; Wu, B. Adaptive segmentation model for liver CT images based on neural network and level set method. Neurocomputing 2021, 453, 438–452. [Google Scholar] [CrossRef]
- Casolla, G.; Cuomo, S.; Di Cola, V.S.; Piccialli, F. Exploring unsupervised learning techniques for the Internet of Things. IEEE Trans. Ind. Inform. 2019, 16, 2621–2628. [Google Scholar] [CrossRef]
- Caron, M.; Bojanowski, P.; Joulin, A.; Douze, M. Deep clustering for unsupervised learning of visual features. In Proceedings of the ECCV, Munich, Germany, 8–14 September 2018; pp. 132–149. [Google Scholar]
- Ren, P.; Xiao, Y.; Chang, X.; Huang, P.; Li, Z.; Gupta, B.B.; Chen, X.; Wang, X. A Survey of Deep Active Learning. ACM Comput. Surv. 2022, 54, 1–40. [Google Scholar] [CrossRef]
- Ren, P.; Xiao, Y.; Chang, X.; Huang, P.; Li, Z.; Chen, X.; Wang, X. A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions. ACM Comput. Surv. 2021, 54, 1–34. [Google Scholar] [CrossRef]
- Crawford, E.; Pineau, J. Exploiting spatial invariance for scalable unsupervised object tracking. In Proceedings of the AAAI, New York, NY, USA, 7–12 February 2020; Volume 34, pp. 3684–3692. [Google Scholar]
- Luo, M.; Chang, X.; Nie, L.; Yang, Y.; Hauptmann, A.G.; Zheng, Q. An Adaptive Semisupervised Feature Analysis for Video Semantic Recognition. IEEE Trans. Cybern. 2018, 48, 648–660. [Google Scholar] [CrossRef]
- Wang, N.; Song, Y.; Ma, C.; Zhou, W.; Liu, W.; Li, H. Unsupervised Deep Tracking. In Proceedings of the CVPR, Long Beach, CA, USA, 15–20 June 2019; pp. 1308–1317. [Google Scholar]
- Sun, J.; Zhang, L.; Zha, Y.; Gonzalez-Garcia, A.; Zhang, P.; Huang, W.; Zhang, Y. Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking. In Proceedings of the ACM MM, Virtual, 20–24 October 2021; pp. 2262–2270. [Google Scholar]
- Luiten, J.; Zulfikar, I.E.; Leibe, B. Unovost: Unsupervised offline video object segmentation and tracking. In Proceedings of the CVPR, Seattle, WA, USA, 16–18 June 2020; pp. 2000–2009. [Google Scholar]
- Wang, G.; Zhou, Y.; Luo, C.; Xie, W.; Zeng, W.; Xiong, Z. Unsupervised visual representation learning by tracking patches in video. In Proceedings of the CVPR, Nashville, TN, USA, 20–25 June 2021; pp. 2563–2572. [Google Scholar]
- Wu, Q.; Wan, J.; Chan, A.B. Progressive unsupervised learning for visual object tracking. In Proceedings of the CVPR, Nashville, TN, USA, 20–25 June 2021; pp. 2993–3002. [Google Scholar]
- Wang, N.; Zhou, W.; Tian, Q.; Hong, R.; Wang, M.; Li, H. Multi-cue correlation filters for robust visual tracking. In Proceedings of the CVPR, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4844–4853. [Google Scholar]
- Bertinetto, L.; Valmadre, J.; Golodetz, S.; Miksik, O.; Torr, P.H. Staple: Complementary Learners for Real-Time Tracking. In Proceedings of the CVPR, Las Vegas, NV, USA, 27–30 June 2016; pp. 1401–1409. [Google Scholar]
- Liu, Q.; Li, X.; He, Z.; Fan, N.; Yuan, D.; Wang, H. Learning deep multi-level similarity for thermal infrared object tracking. IEEE Trans. Multimed. 2021, 23, 2114–2126. [Google Scholar] [CrossRef]
- Dong, X.; Shen, J. Triplet loss in siamese network for object tracking. In Proceedings of the ECCV, Munich, Germany, 8–14 September 2018; pp. 459–474. [Google Scholar]
- Valmadre, J.; Bertinetto, L.; Henriques, J.; Vedaldi, A.; Torr, P.H. End-to-End Representation Learning for Correlation Filter Based Tracking. In Proceedings of the CVPR, Honolulu, HI, USA, 21–26 July 2017; pp. 2805–2813. [Google Scholar]
Trackers | UCDT | SiamMask | STAMT | TADT | MLSSNet | MCCT | BACF | SRDCF | CREST | Staple | HSSNet | HDT | HCF | CFNet | SiamFC | SiamTri | DSiam | UDT | MCFTS |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Ours | [26] | [21] | [40] | [67] | [65] | [14] | [16] | [18] | [66] | [22] | [10] | [39] | [69] | [24] | [68] | [27] | [60] | [42] | |
DM | 53.5 | 55.1 | 53.4 | ||||||||||||||||
HH | 56.5 | 61.8 | 57.5 | ||||||||||||||||
VM | 74.6 | 72.8 | 74.1 | ||||||||||||||||
VS | 60.1 | 58.0 | 55.5 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Shu, X.; Huang, F.; Qiu, Z.; Zhang, X.; Yuan, D. Learning Unsupervised Cross-Domain Model for TIR Target Tracking. Mathematics 2024, 12, 2882. https://doi.org/10.3390/math12182882
Shu X, Huang F, Qiu Z, Zhang X, Yuan D. Learning Unsupervised Cross-Domain Model for TIR Target Tracking. Mathematics. 2024; 12(18):2882. https://doi.org/10.3390/math12182882
Chicago/Turabian StyleShu, Xiu, Feng Huang, Zhaobing Qiu, Xinming Zhang, and Di Yuan. 2024. "Learning Unsupervised Cross-Domain Model for TIR Target Tracking" Mathematics 12, no. 18: 2882. https://doi.org/10.3390/math12182882
APA StyleShu, X., Huang, F., Qiu, Z., Zhang, X., & Yuan, D. (2024). Learning Unsupervised Cross-Domain Model for TIR Target Tracking. Mathematics, 12(18), 2882. https://doi.org/10.3390/math12182882