Abstract
Recent researches on visual tracking have shown significant improvement in accuracy by handling the large uncertainties induced by appearance variation and abrupt motion. Most studies concentrate on random walk based Markov chain Monte Carlo(MCMC) tracking methods which have shown inefficiency in sampling from complex and high-dimensional distributions. This paper proposes an adaptive Hamiltonian Monte Carlo sampling based tracking method within the Bayesian filtering framework. In order to suppress the random walk behavior in Gibbs sampling stage, the ordered over-relaxation method is used to draw the momentum item for the joint state variable. An adaptive step-size based scheme is used to simulate the Hamiltonian dynamics in order to reduce the simulation error and improve acceptance rate of the proposed samples. Furthermore, in designing the appearnce model, we introduce the locality sensitive histogram (LSH) to deal with appearance changes induced by illumination change. The proposed tracking method is compared with several state-of-the-art trackers using different quantitative measures: success rate and abruption capture rate. Extensive experimental results have shown its superiority to several other trackers.
Similar content being viewed by others
References
Brooks S, Gelman A, Jones G, Meng X (2011) Handbook of Markov Chain Monte Carlo. Chapman and Hall/CRC press, USA
He S, Yang Q, Lau RWH, Wang J, Yang M-H (2013) Visual tracking via locality sensitive histograms. In: Proceedings of international conference on computer vision and pattern recognition, Portland, pp 2427–2434
Holder T, Leimkuhler B, Reish S (2001) Explicit variable step-size and time reversible integration. Appl Numer Math 39:367–377
Huang W, Leimkuhler B (1997) The adaptive Verlet method. SIAM J Sci Comput 18:239–256
Isar M, Blake A (1998) CONDENSATION-Conditional density propagation for visual tracking. Int J Comput Vision 29:5–28
Khan Z, Balch T, Dellaert F (2005) MCMC-based particle filter for tracking a variable number of interacting targets. IEEE T Pattern Anal 27:1805–1819
Kwon J, Lee K (2008) Tracking of abrupt motion using Wang- Landau Monte Carlo estimation, Computer Vision-ECCV2008. Lecture Notes in Computer Science, Springer, pp 387–400
Kwon J, Lee K (2010) Visual tracking decomposition. In: Proceedings of the international conference on computer vision and pattern recognition, San Francisco, pp 1269–1276
Kwon J, Lee K (2013) Wang-Landau Monte Carlo-based tracking methods for abrupt motions. IEEE T Pattern Anal 35:1011–1024
Li W, Zhang X, Hu W (2009) Contour tracking with abrupt motion. In: Proceedings of international conference on image processing, Cairo, pp 3593–3596
Li X, Wang F, Lu M, Xiao Z (2012) Performance evaluation of abrupt motion trackers. In: Proceedings of international conference on security. Pattern Analysis, and Cybernetics, Wuhan, pp 20–23
Li X, Hu WM, Shen CH, Zhang ZF, Dick A, van den Hengel A (2013) A survey of appearance models in visual object tracking. ACM Trans Intell Syst Technol 4:1–48
Lin C, Wolf W (2009) MCMC-based feature-guided particle filtering for tracking moving objects from a moving platform. In: Proceedings of the international conference on computer vision workshops, Kyoto, pp 828–833
Lim M, Chan C, Monekosso D, Remagnino P (2014) Refined particle swarm intelligence method for abrupt motion tracking. Inform Sciences 283:267–287
Neal R (1995) Suppressing random walks in markov chain monte carlo using ordered overrelaxation, Technical Report:1–12
Oron S, Bar-Hillel A, Levi D, Avidan S Locally orderless tracking. In: Proceedings of international conference on computer vision and pattern recognition, Rhode Island, pp 1940–1947
Smeulders AWM, Chu DM, Cucchiara R, Calderara S, Dehghan A, Shah M (2014) Visual tracking: an experimental survey. IEEE T Pattern Anal 36:1442–1468
Su Y, Zhao Q, Zhao L, Gu D (2014) Abrupt motion tracking using a visual saliency embedded particle filter. Pattern Recognit 47:1826–1834
Wang F, Lu M (2012) Hamiltonian monte carlo estimator for abrupt motion tracking. In: Proceedings of international conference on pattern recognition, Tsukuba, pp 3066–3069
Wang F, Lu M (2013) Efficient visual tracking via Hamiltonian monte carlo markov chain. Comput J 56:1102–1113
Wang F, Li X, Lu M, Xiao Z (2014) Robust abrupt motion tracking via adaptive Hamiltonian monte carlo sampling, Trends in Artificial Intelligence-PRICAI2014, Lecture Notes in Computer Science. Springer, pp 52–63
Yang H, Shao L, Zheng F, Wang L, Song Z (2011) Recent advances and trends in visual tracking: a review. Neurocomputing 74:3823–3831
Yilmaz A, Javed O, Shah M (2006) Object tracking: a survey. ACM Comput Surv 38(13):1–45
Zhang X, Hu W, Xie N, Bao H, Maybank S (2015) A robust tracking system for low frame rate video. Int J Comput Vis 115:279–304
Zhou X, Lu Y (2010) Abrupt motion tracking via adaptive stochastic approximation Monte Carlo sampling. In: Proceedings of the international conference on computer vision and pattern recognition, San Francisco, pp 1847–1854
Zhou X, Lu Y, Lu J, Zhou J (2012) Abrupt motion tracking via intensively adaptive Markov chain Monte Carlo sampling. IEEE T Image Process 21:789–801
Zhou T, Lu Y, Di H (2014) Nearest neighbor field driven stochastic sampling for abrupt motion tracking. In: Proceedings of the international conference on multimedia and expo, Sichuan, pp 1–6
Zhou T, Lu Y, Lv F, Di H, Zhao Q, Zhang J (2015) Abrupt motion tracking via nearest neighbor field driven stochastic sampling. Neurocomputing 165:350–360
Acknowledgments
This work was supported by the National Natural Science Foundation of China (No.61300082,61272369,61402069), Program for Liaoning Excellent Talents in University No.LJQ2015006, Liaoning Natural Science Foundation No.2015020015.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Wang, F., Li, X. & Lu, M. Adaptive Hamiltonian MCMC sampling for robust visual tracking. Multimed Tools Appl 76, 13087–13106 (2017). https://doi.org/10.1007/s11042-016-3699-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3699-1