Object Relocation Visual Tracking Based on Histogram Filter and Siamese Network in Intelligent Transportation
Abstract
:1. Introduction
- We designed a matching filter arbiter with a hierarchical architecture based on the distance histogram of the candidate objects, which can accurately and quickly find the failure.
- We propose an efficient corrector that generates a template set by backtracking. The corrector relocates the object by Gradient Magnitude Similarity Deviation (GMSD) and the assignment algorithm measurement to increase the tracker’s resistibility to interference.
- Experiments on several challenging benchmarks including VOT-18, GOT-10k, OTB-100, and LaSOT have shown that our proposed tracker is superior to many state-of-the-art trackers.
2. Materials and Methods
2.1. SiamFC++
2.2. Arbiter
2.2.1. Match Filter
2.2.2. Transfer Arbiter
2.3. Corrector
2.3.1. Dynamic Template Set
2.3.2. Assignment Algorithm
- (1)
- Take an initial match M from . The weight calculation between different vertex is shown in Equation (7);
- (2)
- While there exists an augmenting path , remove the matching edges of P from M and add non-matching edges of to (this increases the size of by as starts and ends with a free vertex, i.e., a node that is not part of the matching);
- (3)
- Return .
2.3.3. GMSD Relocation
3. Results
3.1. Dataset Description
3.2. Experiment to Verify the Effectiveness of the Arbiter
3.3. Results on Several Benchmarks
4. Conclusions
Author Contributions
Funding
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- 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] [PubMed] [Green Version]
- Henriques, J.F.; Caseiro, R.; Martins, P.; Batista, J. Exploiting the circulant structure of tracking-by-detection with kernels. In Proceedings of the European Conference on Computer Vision, Florence, Italy, 7–13 October 2012; pp. 702–715. [Google Scholar]
- Danelljan, M.; Robinson, A.; Khan, F.S.; Felsberg, M. Beyond correlation filters: Learning continuous convolution operators for visual tracking. In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; pp. 472–488. [Google Scholar]
- Nam, H.; Han, B. Learning multi-domain convolutional neural networks for visual tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 4293–4302. [Google Scholar]
- Lucas, B.D.; Kanade, T. An iterative image registration technique with an application to stereo vision. In Proceedings of the 7th International Joint Conference on Artificial Intelligence, Vancouver, BC, Canada, 24–28 August 1981. [Google Scholar]
- Nummiaro, K.; Koller-Meier, E.; Van Gool, L. An adaptive color-based particle filter. Image Vis. Comput. 2003, 21, 99–110. [Google Scholar] [CrossRef]
- Comaniciu, D.; Meer, P. Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 2002, 24, 603–619. [Google Scholar] [CrossRef] [Green Version]
- Collins, R.; Zhou, X.; Teh, S.K. An open source tracking testbed and evaluation web site. In Proceedings of the IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Beijing, China, 15–16 October 2005; Volume 2, p. 35. [Google Scholar]
- Avidan, S. Ensemble tracking. IEEE Trans. Pattern Anal. Mach. Intell. 2007, 29, 261–271. [Google Scholar] [CrossRef] [PubMed]
- Suykens, J.A.; Vandewalle, J. Least squares support vector machine classifiers. Neural Process. Lett. 1999, 9, 293–300. [Google Scholar] [CrossRef]
- Kalal, Z.; Mikolajczyk, K.; Matas, J. Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 2011, 34, 1409–1422. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Bosch, A.; Zisserman, A.; Munoz, X. Image classification using random forests and ferns. In Proceedings of the 2007 IEEE 11th International Conference on Computer Vision, Rio De Janeiro, Brazil, 14–21 October 2007; pp. 1–8. [Google Scholar]
- Svetnik, V.; Liaw, A.; Tong, C.; Culberson, J.C.; Sheridan, R.P.; Feuston, B.P. Random forest: A classification and regression tool for compound classification and qsar modeling. J. Chem. Inf. Comput. Sci. 2003, 43, 1947–1958. [Google Scholar] [CrossRef] [PubMed]
- Bolme, D.S.; Beveridge, J.R.; Draper, B.A.; Lui, Y.M. Visual object tracking using adaptive correlation filters. In Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 13–18 June 2010; pp. 2544–2550. [Google Scholar]
- Li, F.; Tian, C.; Zuo, W.; Zhang, L.; Yang, M.-H. Learning spatial-temporal regularized correlation filters for visual tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4904–4913. [Google Scholar]
- Ma, C.; Huang, J.-B.; Yang, X.; Yang, M.-H. Hierarchical convolutional features for visual tracking. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015; pp. 3074–3082. [Google Scholar]
- Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- Tao, R.; Gavves, E.; Smeulders, A.W. Siamese instance search for tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 1420–1429. [Google Scholar]
- Bertinetto, L.; Valmadre, J.; Henriques, J.F.; Vedaldi, A.; Torr, P.H. Fully-convolutional siamese networks for object tracking. In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; pp. 850–865. [Google Scholar]
- Wang, X.; Li, C.; Luo, B.; Tang, J. Sint++: Robust visual tracking via adversarial positive instance generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4864–4873. [Google Scholar]
- He, A.; Luo, C.; Tian, X.; Zeng, W. A twofold siamese network for real-time object tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4834–4843. [Google Scholar]
- Wang, Q.; Zhang, L.; Bertinetto, L.; Hu, W.; Torr, P.H. Fast online object tracking and segmentation: A unifying approach. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 1328–1338. [Google Scholar]
- Lv, N.; Ma, H.; Chen, C.; Pei, Q.; Zhou, Y.; Xiao, F.; Li, J. Remote sensing data augmentation through adversarial training. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 9318–9333. [Google Scholar] [CrossRef]
- Chen, C.; Zhang, Y.; Wang, Z.; Wan, S.; Pei, Q. Distributed computation offloading method based on deep reinforcement learning in icv. Appl. Soft Comput. 2021, 103, 107108. [Google Scholar] [CrossRef]
- Gao, M.; Jin, L.; Jiang, Y.; Guo, B. Manifold Siamese Network: A Novel Visual Tracking ConvNet for Autonomous Vehicles. IEEE Trans. Intell. Transp. Syst. 2020, 21, 1612–1623. [Google Scholar] [CrossRef]
- Fu, S.; Atiquzzaman, M.; Ma, L.; Lee, Y.-J. Signaling cost and performance of sigma: A seamless handover scheme for data networks. Wirel. Commun. Mob. Comput. 2005, 5, 825–845. [Google Scholar] [CrossRef] [Green Version]
- Zhang, J.; Li, Q.; Wang, B.; Chen, C.; Wang, T.; Zhou, Y.; Li, J. Object relocation visual tracking based on siamese network. In Proceedings of the 2021 IEEE International Conference on Smart Internet of Things (SmartIoT), Jeju, Korea, 13–15 August 2021; pp. 95–100. [Google Scholar]
- Wang, Q.; Teng, Z.; Xing, J.; Gao, J.; Hu, W.; Maybank, S. Learning attentions: Residual attentional siamese network for high performance online visual tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4854–4863. [Google Scholar]
- Li, B.; Yan, J.; Wu, W.; Zhu, Z.; Hu, X. High performance visual tracking with siamese region proposal network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 8971–8980. [Google Scholar]
- Ren, S.; He, K.; Girshick, R.; Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 2015, 28, 91–99. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Li, B.; Wu, W.; Wang, Q.; Zhang, F.; Xing, J.; Yan, J. Siamrpn++: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, 15–20 June 2019; pp. 4282–4291. [Google Scholar]
- Zhang, Z.; Peng, H. Deeper and wider siamese networks for real-time visual tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 4591–4600. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Amsterdam, The Netherlands, 11–14 October 2016; pp. 770–778. [Google Scholar]
- Xu, Y.; Wang, Z.; Li, Z.; Yuan, Y.; Yu, G. Siamfc++: Towards robust and accurate visual tracking with target estimation guidelines. In Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA, 7–12 February 2020; Volume 34, pp. 12549–12556. [Google Scholar]
- Guo, D.; Wang, J.; Cui, Y.; Wang, Z.; Chen, S. Siamcar: Siamese fully convolutional classification and regression for visual tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 6269–6277. [Google Scholar]
- Hopcroft, J.E.; Karp, R.M. An nˆ5/2 algorithm for maximum matchings in bipartite graphs. SIAM J. Comput. 1973, 2, 225–231. [Google Scholar] [CrossRef]
- Kuhn, H.W. The hungarian method for the assignment problem. Nav. Res. Logist. (NRL) 2005, 52, 7–21. [Google Scholar] [CrossRef]
Challenge | Ratio |
---|---|
Distractor | 0.3 |
Deformation | |
Scale variation | 0.1 |
Occlusion | 0.1 |
Other |
Notation | Meaning | Remarks |
---|---|---|
Length of the video frames | N.A. | |
-th similarity score of the bounding Box in the -th frame | N.A. | |
Bounding box set in -th frame | ||
Candidate object set in the-th frame | ||
-th candidate object | ||
-th template | ||
Set of tracking failure frames | ||
Number of candidate objects | N.A. | |
Number of winners | N.A. | |
-th center of the object | ||
Frequency of the -th bin in the histogram |
Dataset | Number of Scenarios | TVAR | TIAR |
---|---|---|---|
OTB-15 | 100 | 0.86 | 0.68 |
VOT-18 | 60 | 0.81 | 0.59 |
GOT-10k | 280 | 0.90 | 0.82 |
LaSOT | 180 | 0.67 | 0.40 |
Tracker | SiamFC | ECO | SiamRPN++ | ATOM | SiamFC++ | Ours |
---|---|---|---|---|---|---|
OTB-15 Success | 58.2 | 70.0 | 69.6 | 66.9 | 68.3 | 72.7 |
VOT-18 Accuracy [1] | 0.412 | 0.404 | 0.484 | 0.478 | 0.480 | 0.533 |
LaSOT Success | 33.6 | 32.4 | 49.6 | 51.5 | 54.5 | 57.5 |
GOT-10k AO | 34.8 | 31.6 | 51.8 | 55.6 | 59.5 | 61.2 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 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
Zhang, J.; Liu, Y.; Li, Q.; He, C.; Wang, B.; Wang, T. Object Relocation Visual Tracking Based on Histogram Filter and Siamese Network in Intelligent Transportation. Sensors 2022, 22, 8591. https://doi.org/10.3390/s22228591
Zhang J, Liu Y, Li Q, He C, Wang B, Wang T. Object Relocation Visual Tracking Based on Histogram Filter and Siamese Network in Intelligent Transportation. Sensors. 2022; 22(22):8591. https://doi.org/10.3390/s22228591
Chicago/Turabian StyleZhang, Jianlong, Yifan Liu, Qiao Li, Ci He, Bin Wang, and Tianhong Wang. 2022. "Object Relocation Visual Tracking Based on Histogram Filter and Siamese Network in Intelligent Transportation" Sensors 22, no. 22: 8591. https://doi.org/10.3390/s22228591