Skip to main content
SpringerLink
Log in

Probabilistic Matrix Factorization for Visual Tracking

  • MATHEMATICAL THEORY OF IMAGES AND SIGNALS REPRESENTING, PROCESSING, ANALYSIS, RECOGNITION, AND UNDERSTANDING
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

In visual tracking, designing an effective and robust target appearances remains a challenging work due to variations of complicated target appearances and other challenging factors, such as drastic illumination variations, object rotations, partial occlusions, nonrigid deformation, and fast motion. Existing tracking algorithms use previous tracking results as target templates to represent a target candidate. Such target representations are not robust to drastic appearance variations. In this paper, we represent a target candidate as a linear combination of a set of matrix basis. These bases are obtained from a probabilistic matrix factorization, which are learned from previous tracking result examples. The learned matrix basis can capture target structure information and local information. The matrix factorization based on previous tracking result examples over frames can learn target appearance variations in the tracking process. Such target representation is robust to shape variations and outliers. With this kind of target appearances, we propose a novel tracking algorithm in a particle filter framework. Extensive experiments conducted on some challenging video sequences demonstrate the proposed tracking algorithm is effective and robust to outliers and other complicated appearance variations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.

Similar content being viewed by others

REFERENCES

  1. B. Babenko, M. Yang, and S. Belongie, “Robust object tracking with online multiple instance learning,” IEEE Trans. Pattern Anal. Mach. Intell. 33, 1619–1632 (2011).  https://doi.org/10.1109/TPAMI.2010.226

    Article  Google Scholar 

  2. Q. Bai, Z. Wu, S. Sclaroff, M. Betke, and C. Monnier, “Randomized ensemble tracking,” in IEEE Int. Conf. on Computer Vision, Sydney, 2013 (IEEE, 2013), pp. 2040–2047. https://doi.org/10.1109/ICCV.2013.255

  3. L. Bertinetto, J. Valmadre, J. F Henriques, A. Vedaldi, and P. Torr, “Fully-convolutional siamese networks for object tracking,” in Computer Vision–ECCV 2016 Workshops, Ed. by G. Hua and H. Jégou, Lecture Notes in Computer Science, vol. 9914 (Springer, Cham, 2016), pp. 850–865.  https://doi.org/10.1007/978-3-319-48881-3_56

    Book  Google Scholar 

  4. L. Bertinetto, J. Valmadre, S. Golodetz, O. Miksik, and P. Torr, “Staple: Complementary learners for real-time tracking,” in IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, 2016 (IEEE, 2016), pp. 1401–1409.  https://doi.org/10.1109/CVPR.2016.156

  5. Z. Chi, H. Li, H. Hu, and M. Yang, “Dual deep network for visual tracking,” IEEE Trans. Image Process. 26, 2005–2015 (2017). https://doi.org/10.1109/TIP.2017.2669880

    Article  MathSciNet  MATH  Google Scholar 

  6. J. Choi, H. Chang, S. Yun, T. Fischer, and Y. Jin, “Attentional correlation filter network for adaptive visual tracking,” in IEEE Conf. on Computer Vision and Pattern Recognition, Honolulu, Hawaii, 2017 (IEEE, 2017), pp. 4828–4837. https://doi.org/10.1109/CVPR.2017.513

  7. J. Gao, H. Ling, W. Hu, and J. Xing, “Transfer learning based visual tracking with Gaussian processes regression,” in Computer Vision–ECCV 2014, Ed. by D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars (Springer, Cham, 2014), pp. 188–203. https://doi.org/10.1007/978-3-319-10578-9_13

  8. J. Gao, T. Zhang, and C. Xu, “Graph convolutional tracking,” in IEEE Conf. on Computer Vision and Pattern Recognition, 2019, (IEEE, 2019), pp. 4649–4659. https://doi.org/10.1109/CVPR.2019.00478

  9. Q. Guo, W. Feng, C. Zhou, R. Huang, L. Wan, and S. Wang, “Learning dynamic siamese network for visual object tracking,” in IEEE Int. Conf. on Computer Vision, Venice, 2017 (IEEE, 2017), pp. 1781–1789.  https://doi.org/10.1109/ICCV.2017.196

  10. S. Hare, A. Saffari, and P. H. S. Torr, “Struck: Structured output tracking with kernels,” in Int. Conf. on Computer Vision, Barcelona, 2011 (IEEE, 2011), pp. 263–270. https://doi.org/10.1109/ICCV.2011.6126251

  11. S. He, Q. Yang, R. Lau, J. Wang, and M. Yang, “Visual tracking via locality sensitive histograms,” in IEEE Conf. on Computer Vision and Pattern Recognition, Portland, Ore., 2013 (IEEE, 2013), pp. 2427–2434. https://doi.org/10.1109/CVPR.2013.314

  12. J. Henriques, R. Caseiro, P. Martins, and J. Batista, “High-speed tracking with kernelized correlation filters,” IEEE Trans. Pattern Anal. Mach. Intell. 37, 583–596 (2014). https://doi.org/10.1109/TPAMI.2014.2345390

    Article  Google Scholar 

  13. Z. Huang, C. Fu, Y. Li, F. Lin, and P. Lu, “Learning aberrance repressed correlation filter for real-time UAV tracking,” in IEEE/CVF Int. Conf. on Computer Vision (ICCV), Seoul, 2019 (IEEE, 2019), pp. 2891–2900. https://doi.org/10.1109/ICCV.2019.00298

  14. M. Isard, and A. Blake, “CONDENSATION—conditional density propagation for visual tracking,” Int. J. Comput. Vision 29, 5–28 (1998). https://doi.org/10.1023/A:1008078328650

    Article  Google Scholar 

  15. X. Jia, H. Lu, and M. Yang, “Visual tracking via adaptive structural local sparse appearance model,” in IEEE Conf. on Computer Vision and Pattern Recognition, Providence, R.I., 2012 (IEEE, 2012), pp. 1822–1829. https://doi.org/10.1109/CVPR.2012.6247880

  16. A. Krizhevsky, I. Sutskever, and G. E Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. of the 25th Int. Conf. on Neural Information Processing Systems, Lake Tahoe, Nev., 2012 (Curran Associates, Red Hook, N.Y., 2012), vol. 1, pp. 1097–1105.

  17. X. Li, Y. Zha, T. Zhang, Z. Cui, W. Zuo, Z. Hou, H. Lu, and H. Wang, “Survey of visual object tracking algorithms based deep learning,” J. Image Graphics 24, 2057–2080 (2019).

    Google Scholar 

  18. S. Liu, T. Zhang, X. Cao, and C. Xu, “Structural correlation filter for robust visual tracking,” in IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016 (IEEE, 2016), pp. 4312–4320. https://doi.org/10.1109/CVPR.2016.467

  19. C. Ma, J.-B. Huang, X. Yang, and M.-H. Yang, “Hierarchical convolutional features for visual tracking,” in IEEE Int. Conf. on Computer Vision, Santiago, 2015 (IEEE, 2015), pp. 3074–3082. https://doi.org/10.1109/ICCV.2015.352

  20. X. Mei and H. Ling, “Robust visual tracking and vehicle classification via sparse representation,” IEEE Trans. Pattern Anal. Mach. Intell. 33, 2259–2272 (2011). https://doi.org/10.1109/TPAMI.2011.66

    Article  Google Scholar 

  21. H. Nam and B. Han, “Learning multi-domain convolutional neural networks for visual tracking,” in IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016 (IEEE, 2016), pp. 4293–4302. https://doi.org/10.1109/CVPR.2016.465

  22. X. Ren and D. Ramanan, “Histograms of sparse codes for object detection,” in IEEE Conf. on Computer Vision and Pattern Recognition, Portland, Ore., 2013 (IEEE, 2013), pp. 3246–3253. https://doi.org/10.1109/CVPR.2013.417

  23. D. Wang, H. Lu, and M. Yang, “Least soft-threshold squares tracking,” in IEEE Int. Conf. on Computer Vision and Pattern Recognition, Portland, Ore., 2013 (IEEE, 2013), pp. 2371–2378. https://doi.org/10.1109/CVPR.2013.307

  24. N. Wang, T. Yao, J. Wang, and D.-Y. Yeung, “A probabilistic approach to robust matrix factorization,” in Computer Vision–ECCV 2012, Ed. by A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, and C. Schmid, Lecture Notes in Computer Science, vol. 7578 (Springer, Berlin, 2012), pp. 126–139. https://doi.org/10.1007/978-3-642-33786-4_10

    Book  Google Scholar 

  25. N. Wang, W. Zhou, Q. Tian, R. Hong, M. Wang, and H. Li, “MultiCue correlation filters for robust visual tracking,” in IEEE Conf. on Computer Vision and Pattern Recognition, Salt Lake City, Utah, 2018 (IEEE, 2018), pp. 4844–4853. https://doi.org/10.1109/CVPR.2018.00509

  26. Y. Wu, J. Lim, and M. Yang, “Object tracking benchmark,” IEEE Trans. Pattern Anal. Mach. Intell. 37, 1834–1848 (2015). https://doi.org/10.1109/TPAMI.2014.2388226

    Article  Google Scholar 

  27. Y. Xie, W. Zhang, C. Li, S. Lin, Y. Qu, and Y. Zhang, “Discriminative object tracking via sparse representation and online dictionary learning,” IEEE Trans. Cybern. 44, 539–553 (2014). https://doi.org/10.1109/TCYB.2013.2259230

    Article  Google Scholar 

  28. A. Yilmaz, O. Javed, and M. Shah, “Object tracking: A survey,” ACM Comput. Surv. 38 (4), 1–45 (2006). https://doi.org/10.1145/1177352.1177355

    Article  Google Scholar 

  29. T. Zhang, S. Liu, N. Ahuja, M. Yang, and B. Ghanem, “Robust visual tracking via consistent low-rank sparse learning,” Int. J. Comput. Vision 111, 171–190 (2015).  https://doi.org/10.1007/s11263-014-0738-0

    Article  MATH  Google Scholar 

  30. T. Zhang, C. Xu, and M.-H. Yang, “Robust structure sparse tracking,” IEEE Trans. Pattern Anal. Mach. Intell. 41, 473–486 (2019). https://doi.org/10.1109/TPAMI.2018.2797082

    Article  Google Scholar 

  31. T. Zhang, C. Xu, and M.-H. Yang, “Multi-task correlation particle filter for robust object tracking, in IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017 (IEEE, 2017), pp. 4819–4827. https://doi.org/10.1109/CVPR.2017.512

  32. H. Zhao, G. Yang, D.Wang, and H. Lu, “Lightweight deep neural network for real-time visual tracking with mutual learning,” in IEEE Int. Conf. on Image Processing, Taipei, 2019 (IEEE, 2019), pp. 3063–3067. https://doi.org/10.1109/ICIP.2019.8803340

  33. W. Zhong, H. Lu, and M. Yang, “Robust object tracking via sparsity-based collaborative model,” in IEEE Conf. on Computer Vision and Pattern Recognition, Providence, R.I., 2012 (IEEE, 2012), pp. 1838–1845. https://doi.org/10.1109/CVPR.2012.6247882

Download references

Author information

Authors and Affiliations

  1. School of Qianhu, Nanchang University, 330029, Nanchang, China

    Xinyi Wei

  2. Department of Computer Science and Technology, Nanchang University, 330029, Nanchang, China

    Zhenrong Lin, Tao Liu & Le Zhang

Authors
  1. Xinyi Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhenrong Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Le Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Xinyi Wei, Zhenrong Lin, Tao Liu or Le Zhang.

Ethics declarations

COMPLIANCE WITH ETHICAL STANDARDS

This article is a completely original work of its authors; it has not been published before and will not be sent to other publications until the PRIA Editorial Board decides not to accept it for publication.

Conflict of Interest

The authors declare that they have no conflicts of interest.

Additional information

Xinyi Wei, is an undergraduate in Nanchang University and is now in her junior year. Her research interests include image processing, machine learning, and artificial intelligence.

Zhenrong Lin, is an Associate Professor and postgraduate tutor in the Computer Science and Technology Department of Information and Engineering School in Nanchang University. His research interests include image processing, visual tracking, and information security.

Tao Liu, is a MS candidate. His research interest includes artificial intelligence.

Le Zhang, is a lecturer in the Department of Computer Science and Technology, Nanchang University. His research interest includes visual tracking and data mining.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xinyi Wei, Lin, Z., Liu, T. et al. Probabilistic Matrix Factorization for Visual Tracking. Pattern Recognit. Image Anal. 32, 57–66 (2022). https://doi.org/10.1134/S1054661822010114

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661822010114

Keywords:

Search

Navigation