Skip to main content
Log in

Discriminative anisotropic propagation with heat source estimation for robust object tracking

  • Neural Computing in Next Generation Virtual Reality Technology
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Anisotropic propagations have been widely used for image processing for decades. However, most previous anisotropic propagations are simply defined on regular image pixels and cannot be used for complex vision task, e.g., object tracking. Tracking as a fundamental task in computer vision has potential value for virtual reality (VR) and augmented reality (AR). In this paper, we proposed a novel discriminative anisotropic propagations model called sequential heat diffusions (SHD) on video sequences to address this issue. Our core idea is to propagate the discriminative appearance of the target object on both the temporal and spatial domains. In particular, we first train a discriminative appearance model for the target. Then for a coming frame, we design two coupled diffusions, in which the spatial one estimates a probability to reflect the intrinsic object structure and the temporal one also provides another probability (guided by information of training frames) to capture the background distribution. Finally, the tracking result is achieved by maximizing a combined confidence maps. The experiments on many challenging videos show the superiority of our method against other state-of-the-art trackers.

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

Access this article

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
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Klein G (2006) Visual tracking for augmented reality. PhD thesis, University of Cambridge

  2. Klein G, Drummond T (2003) Robust visual tracking for non-instrumental augmented reality. In: The Second IEEE and ACM international symposium on mixed and augmented reality, 2003. Proceedings. IEEE, pp 113–122

  3. Liu R, Cao J, Lin Z, Shan S (2014) Adaptive partial differential equation learning for visual saliency detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3866–3873

  4. Yilmaz, Javed O, Shah M (2006) Object tracking: a survey. Acm Comput Surv (CSUR) 38(4):13

    Article  Google Scholar 

  5. Ross DA, Lim J, Lin R-S, Yang M-H (2008) Incremental learning for robust visual tracking. Int J Comput Vis 77(1–3):125–141

    Article  Google Scholar 

  6. Bao C, Yi W, Ling H, Ji H (2012) Real time robust l1 tracker using accelerated proximal gradient approach. In: 2012 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 1830–1837

  7. Zhang T, Ghanem B, Si L, Ahuja N (2012) Robust visual tracking via multi-task sparse learning. In: 2012 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 2042–2049

  8. Hare S, Saffari A, Torr PHS (2016) Struck: structured output tracking with kernels. 2011 IEEE Trans Pattern Anal Mach Intell 38(10):2096–2109

    Article  Google Scholar 

  9. Adam A, Rivlin E, Shimshoni I (2006) Robust fragments-based tracking using the integral histogram. In: 2006 IEEE Computer society conference on computer vision and pattern recognition (CVPR’06), vol 1. IEEE, pp 798–805

  10. Wang S, Huchuan L, Yang F, Yang M-H (2011) Superpixel tracking. In: 2011 International conference on computer vision. IEEE, pp 1323–1330

  11. Yi W, Lim J, Yang M-H (2013) Online object tracking: a benchmark. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2411–2418

  12. Bai S, Liu R, Zhixun S, Zhang C, Jin W (2014) Incremental robust local dictionary learning for visual tracking. In: 2014 IEEE international conference on multimedia and expo (ICME). IEEE, pp 1–6

  13. Yang S, Wong-Lin KF, Andrew J, MakT T, McGinnity M (2017) A neuro-inspired visual tracking method based on programmable system-on-chip platform. Neural Comput Appl 1–12

  14. Almomani R, Dong M, Zhu D (2016) Object tracking via Dirichlet process-based appearance models. Neural Comput Appl 1–13

  15. Cheng MDS, He X (2016) Hybrid generative–discriminative hash tracking with spatio-temporal contextual cues. Neural Comput Appl 1–11

  16. Liu R, Jin W, Zhixun S, Zhang C (2014) Latent subspace projection pursuit with online optimization for robust visual tracking. IEEE MultiMed 21(4):47–55

    Article  Google Scholar 

  17. Wang D, Huchuan L, Bo C (2015) Fast and robust object tracking via probability continuous outlier model. IEEE Trans Image Process 24(12):5166–5176

    Article  MathSciNet  Google Scholar 

  18. Di W, Liu R, Zhixun S (2015) Robust visual tracking via guided low-rank subspace learning. In: 2015 IEEE International conference on image processing (ICIP). IEEE, pp 1–5

  19. Deng Y, Kong Y, Bao F, Dai Q (2016) Deep and structured robust information theoretic learning for image analysis. IEEE Trans Indus Inf 11(2):467–475

    Article  Google Scholar 

  20. Zhang L, Zhang Q, Zhang L, Tao D, Huang X, Du B (2015) Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding. Pattern Recogn 48(10):3102–3112

    Article  Google Scholar 

  21. Deng Y, Li Y, Qian Y, Ji X, Dai Q (2014) Visual words assignment via information-theoretic manifold embedding. IEEE Trans Cybern 44(10):1924–1937

    Article  Google Scholar 

  22. Zhong G, Liu R, Zhixun S (2015) Robust visual tracking via discriminative sequential ranking. In: 2015 IEEE International conference on image processing (ICIP). IEEE, pp 1354–1358

  23. Kalal Z, Matas J, Mikolajczyk K (2010) Pn learning: bootstrapping binary classifiers by structural constraints. In: 2010 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 49–56

  24. Zhang K, Liu Q, Yi W, Yang M-H (2016) Robust visual tracking via convolutional networks without training. IEEE Trans Image Process 25(4):1779–1792

    MathSciNet  Google Scholar 

  25. Patan G G, Falcidieno B (2010) Multi-scale feature spaces for shape processing and analysis. In: Shape modeling international, pp 113–123

  26. Ovsjanikov M, Facundo, Guibas L (2010) One point isometric matching with the heat kernel. Comput Graph Forum 29(5):1555–1564

    Article  Google Scholar 

  27. Bronstein A M, Bronstein MM, Guibas LJ, Ovsjanikov M (2011) Shape google: geometric words and expressions for invariant shape retrieval. ACM Trans Graph (TOG) 30(1):1

    Article  Google Scholar 

  28. Liu R, Zhong G, Cao J, Lin Z, Luo Z et al (2016) Learning to diffuse: a new perspective to design pdes for visual analysis

  29. Deng Y, Dai Q, Zhang Z (2011) Graph Laplace for occluded face completion and recognition. IEEE Trans Image Process 20(8):2329–2338

    Article  MathSciNet  MATH  Google Scholar 

  30. Kim G, Xing EP, Fei-Fei L, Kanade T (2011) Distributed cosegmentation via submodular optimization on anisotropic diffusion. In: 2011 IEEE International conference on computer vision (ICCV), pp 169–176

  31. Zhang J, Zheng J, Cai J (2010) A diffusion approach to seeded image segmentation. In: 2010 IEEE Conference on computer vision and pattern recognition (CVPR), pp 2125–2132

  32. Lopez-Molina C, Galar M, Bustince H, De Baets B (2014) On the impact of anisotropic diffusion on edge detection. Pattern Recogn 47(1):270–281

    Article  Google Scholar 

  33. Zhang C, Liu R, Qiu T, Zhixun S (2014) Robust visual tracking via incremental low-rank features learning. Neurocomputing 131:237–247

    Article  Google Scholar 

  34. Babenko B, Yang M-H, Belongie S (2009) Visual tracking with online multiple instance learning. In: IEEE Conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 983–990

  35. Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282

    Article  Google Scholar 

  36. Smola A J, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222

    Article  MathSciNet  Google Scholar 

  37. Henriques JF, Caseiro R, Martins P, Batista J (2015) High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37(3):583–596

    Article  Google Scholar 

  38. Wang N, Yeung D-Y (2013) Learning a deep compact image representation for visual tracking. In: Advances in neural information processing systems, pp 809–817

  39. Zhang K, Zhang L, Liu Q, Zhang D, Yang M-H (2014) Fast visual tracking via dense spatio-temporal context learning. In: European conference on computer vision. Springer, pp 127– 141

  40. Henriques J F, Caseiro R, Martins Po, Batista J (2012) Exploiting the circulant structure of tracking-by-detection with kernels. In: European conference on computer vision. Springer, pp 702– 715

  41. Wang D, Huchuan L (2014) Visual tracking via probability continuous outlier model. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3478– 3485

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Risheng Liu.

Ethics declarations

Conflict of interests

The authors declare that they have no conflict of interest.

Funding

R. Liu is supported by the National Science Foundation of China (NSFC) (Nos. 61672125, 61300086), the Fundamental Research Funds for the Central Universities (No. DUT15QY15), and the Hong Kong Scholar Program (No. XJ2015008). Z. Luo is supported by the National Natural Science Foundation of China (NSFC) (Grant Nos. 61432003, 61572105, 11171052, 61328206). X. Fan is supported by the National Science Foundation of China (NSFC) (No. 61572096). H. Li is supported by the National Science Foundation of China (NSFC) (No. 61472059).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, Y., Liu, R., Zhong, G. et al. Discriminative anisotropic propagation with heat source estimation for robust object tracking. Neural Comput & Applic 29, 1267–1279 (2018). https://doi.org/10.1007/s00521-017-3031-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-017-3031-7

Keywords

Navigation