Abstract
We present a novel tracking system that adaptively selects a shape of the posterior over time, where the selection is efficiently performed by the uncertainty calibrated Markov Chain Monte Carlo (UCMCMC) sampler. In conventional trackers, the posterior is typically described by a single prior distribution. On the other hand, our tracker allows the posterior to have multiple prior distributions, namely normal and Student’s t distribution, and to choose an appropriate distribution according to the tracking environment. The optimal distribution is determined by the UCMCMC sampler in the process of reducing the uncertainty of the shape. Experimental results demonstrate that the proposed multi-shape posterior helps improve the tracking performance in terms of accuracy.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
The degree of freedom \(\nu \) used in this test is \(n-1\).
References
Abbasnejad, E., Domke, J., Sanner, S.: Loss-calibrated monte carlo action selection. In: AAAI (2015)
Bibi, A., Mueller, M., Ghanem, B.: Target response adaptation for correlation filter tracking. In: ECCV (2016)
Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: CVPR (2010)
Danelljan, M., Khan, F.S., Felsberg, M., van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR (2014)
Danelljan, M., Robinson, A., Khan, F., Felsberg, M.: Beyond correlation filters: Learning continuous convolution operators for visual tracking. In: ECCV (2016)
Dinh, T.B., Vo, N., Medioni, G.: Context tracker: exploring supporters and distracters in unconstrained environments. In: CVPR (2011)
Hare, S., Saffari, A., Torr, P.: Struck: structured output tracking with kernels. In: ICCV (2011)
He, S., Yang, Q., Lau, R., Wang, J., Yang, M.H.: Visual tracking via locality sensitive histograms. In: CVPR (2013)
Henriques, J., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: ECCV (2012)
Henriques, J., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. PAMI 37(3), 583–596 (2015)
Hong, S., You, T., Kwak, S., Han, B.: Online tracking by learning discriminative saliency map with convolutional neural network. In ICML (2015)
Isard, M., Blake, A.: Icondensation: Unifying low-level and high-level tracking in a stochastic framework. In: ECCV (1998)
Jia, X., Lu, H., Yang, M.H.: Visual tracking via adaptive structural local sparse appearance model (2012)
Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking–learning–detection. PAMI 34(7), 1409–1422 (2012)
Khan, Z., Balch, T., Dellaert, F.: MCMC-based particle filtering for tracking a variable number of interacting targets. PAMI 27(11), 1805–1918 (2005)
Kwon, J., Dragon, R., Gool, L.V.: Joint tracking and ground plane estimation. IEEE Signal Process. Lett. 23(11), 1514–1517 (2016)
Kwon, J., Lee, K.M.: Visual tracking decomposition. In: CVPR (2010)
Kwon, J., Lee, K.M.: Tracking by sampling trackers. In: ICCV (2011)
Kwon, J., Lee, K.M.: Interval tracker: tracking by interval analysis. In: CVPR (2014)
Kwon, J., Roh, J., Lee, K.M., Van Gool, L.: Robust visual tracking with double bounding box model. In: ECCV (2014)
Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: ICCV (2015)
Li, H., Li, Y., Porikli, F.: Deeptrack: learning discriminative feature representations by convolutional neural networks for visual tracking. In: BMVC (2014)
Liu, B., Huang, J., Yang, L., Kulikowsk, C.: Robust tracking using local sparse appearance model and k-selection. In: CVPR (2011)
Loxam, J., Drummond, T.: Student-\(t\) mixture filter for robust, real-time visual tracking. In: ECCV (2008)
Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: CVPR (2016)
Perez, P., Hue, C., Vermaak, J., Gangnet, M.: Color-based probabilistic tracking. In: ECCV (2002)
Roh, J., Park, D.W., Kwon, J., Lee, K.M.: Visual tracking using joint inference of target state and segment-based appearance models. In: APSIPA (2013)
Ross, D., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. IJCV 77(1), 125–141 (2008)
Sevilla-Lara, L., Learned-Miller, E.G.: Distribution fields for tracking. In: CVPR (2012)
Sui, Y., Zhang, Z., Wang, G., Tang, Y., Zhang, L.: Real-time visual tracking: promoting the robustness of correlation filter learning. In: ECCV (2016)
Tao, R., Gavves, E., Smeulders, A.W.: Siamese instance search for tracking. In: CVPR (2016)
Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR (2013)
Zhang, J., Ma, S., Sclaroff, S.: MEEM: robust tracking via multiple experts using entropy minimization. In: ECCV (2014)
Zhang, T., Ghanem, B., Liu, S., Ahuja, N.: Robust visual tracking via multi-task sparse learning. In: CVPR (2012)
Zhong, W., Lu, H., Yang, M.H.: Robust object tracking via sparsity-based collaborative model. In: CVPR (2012)
Acknowledgements
This work was supported by the National Research Foundation of Korea (NRF) Grant funded by the Korea government (No. 2017R1C1B1003354).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kwon, J. Uncertainty Calibrated Markov Chain Monte Carlo Sampler for Visual Tracking Based on Multi-shape Posterior. J Math Imaging Vis 60, 681–691 (2018). https://doi.org/10.1007/s10851-017-0783-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-017-0783-8