Abstract
Although ‘tracking-by-detection’ is a popular approach when reliable object detectors are available, missed detections remain a difficult hurdle to overcome. We present a hybrid stochastic/deterministic optimization scheme that uses RJMCMC to perform stochastic search over the space of detection configurations, interleaved with deterministic computation of the optimal multi-frame data association for each proposed detection hypothesis. Since object trajectories do not need to be estimated directly by the sampler, our approach is more efficient than traditional MCMCDA techniques. Moreover, our holistic formulation is able to generate longer, more reliable trajectories than baseline tracking-by-detection approaches in challenging multi-target scenarios.
Chapter PDF
Similar content being viewed by others
Keywords
- Markov Chain Monte Carlo
- Ground Plane
- Data Association
- Markov Chain Monte Carlo Sampler
- Deterministic Optimization
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Alahi, A., Jacques, L., Boursier, Y., Vandergheynst, P.: Sparsity driven people localization with a heterogeneous network of cameras. Journal of Mathematical Imaging and Vision 41(1-2), 39–58 (2011)
Andriyenko, A., Schindler, K., Roth, S.: Discrete-continuous optimization for multi-target tracking. In: CVPR (2012)
Ben Shitrit, H., Berclaz, J., Fleuret, G., Fua, P.: Multi-Commodity Network Flow for Tracking Multiple People. PAMI (2013)
Benfold, B., Reid, I.: Stable multi-target tracking in real-time surveillance video. In: CVPR (2011)
Berclaz, J., Turetken, E., Fleuret, F., Fua, P.: Multiple Object Tracking using K-Shortest Paths Optimization. PAMI 33(9), 1806–1819 (2011)
Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: The CLEAR MOT metrics. EURASIP Journal on Image and Video Processing, Special Issue on Video Tracking in Complex Scenes for Surveillance Applications 2008, article ID 246309 (May 2008)
Brau, E., Barnard, K., Palanivelu, R., Dunatunga, D., Tsukamoto, T., Lee, P.: A generative statistical model for tracking multiple smooth trajectories. In: CVPR, pp. 1137–1144 (2011)
Breitenstein, M., Reichlin, F., Leibe, B., Koller-Meier, E., Van Gool, L.: Online multiperson tracking-by-detection from a single, uncalibrated camera. PAMI 33(9), 1820–1833 (2011)
Brendel, W., Amer, M., Todorovic, S.: Multiobject tracking as maximum weight independent set. In: CVPR (2011)
Carr, P., Sheikh, Y., Matthews, I.: Monocular object detection using 3D geometric primitives. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 864–878. Springer, Heidelberg (2012)
Collins, R.: Multitarget data association with higher-order motion models. In: CVPR (2012)
Fleuret, F., Berclaz, J., Lengagne, R., Fua, P.: Multi-Camera People Tracking with a Probabilistic Occupancy Map. PAMI 30(2), 267–282 (2008)
Ge, W., Collins, R.: Marked point processes for crowd counting. In: CVPR. pp. 2913–2920 (2009)
Ge, W., Collins, R.: Multi-target data association by tracklets with unsupervised parameter estimation. In: BMVC (2008)
Green, P.: Reversible jump markov chain monte carlo computation and bayesian model determination. Biometrika 82(4), 711–732 (1995)
Huang, C., Wu, B., Nevatia, R.: Robust object tracking by hierarchical association of detection responses. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 788–801. Springer, Heidelberg (2008)
Khan, Z., Balch, T., Dellaert, F.: Mcmc data association and sparse factorization updating for real time multitarget tracking with merged and multiple measurements. PAMI 28(12), 1960–1972 (2006)
Kim, W., Lee, K.: Markov chain monte carlo combined with deterministic methods for markov random field optimization. In: CVPR (2009)
Leibe, B., Schindler, K., Gool, L.J.V.: Coupled detection and trajectory estimation for multi-object tracking. In: ICCV, pp. 1–8 (2007)
van Lieshout, M.: Depth map calculation for a variable number of moving objects using markov sequential object processes. PAMI 30(7), 1308–1312 (2008)
Milan, A., Roth, S., Schindler, K.: Continuous energy minimization for multitarget tracking. PAMI 36(1), 58–72 (2014)
Oh, S., Russell, S., Sastry, S.: Markov chain monte carlo data association for multi-target tracking. IEEE Transactions on Automatic Control 54(3), 481–497 (2009)
Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR (2011)
Possegger, H., Sternig, S., Mauthner, T., Roth, P., Bischof, H.: Robust real-time tracking of multiple objects by volumetric mass densities. In: CVPR, pp. 2395–2402 (2013)
Shafique, K., Shah, M.: A noniterative greedy algorithm for multiframe point correspondence. PAMI 27(1), 51–65 (2005)
Wu, Z., Thangali, A., Sclaroff, S., Betke, M.: Coupling detection and data association for multiple object tracking. In: CVPR, pp. 1–8. Rhode Island (June 2012)
Roshan Zamir, A., Dehghan, A., Shah, M.: Gmcp-tracker: Global multi-object tracking using generalized minimum clique graphs. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 343–356. Springer, Heidelberg (2012)
Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: CVPR (2008)
Zhao, T., Nevatia, R.: Bayesian human segmentation in crowded situations. In: CVPR (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Collins, R.T., Carr, P. (2014). Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8690. Springer, Cham. https://doi.org/10.1007/978-3-319-10605-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-10605-2_20
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10604-5
Online ISBN: 978-3-319-10605-2
eBook Packages: Computer ScienceComputer Science (R0)