Advertisement

Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians

  • Robert T. Collins
  • Peter Carr
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8690)

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.

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.

Supplementary material

978-3-319-10605-2_20_MOESM1_ESM.mp4 (12.8 mb)
Electronic Supplementary Material (MP4 13,129 KB)
978-3-319-10605-2_20_MOESM2_ESM.mp4 (7.6 mb)
Electronic Supplementary Material (MP4 7,827 KB)
978-3-319-10605-2_20_MOESM3_ESM.mp4 (4.3 mb)
Electronic Supplementary Material (MP4 4,387 KB)
978-3-319-10605-2_20_MOESM4_ESM.pdf (96 kb)
Electronic Supplementary Material (PDF 97 KB)

References

  1. 1.
    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)CrossRefzbMATHMathSciNetGoogle Scholar
  2. 2.
    Andriyenko, A., Schindler, K., Roth, S.: Discrete-continuous optimization for multi-target tracking. In: CVPR (2012)Google Scholar
  3. 3.
    Ben Shitrit, H., Berclaz, J., Fleuret, G., Fua, P.: Multi-Commodity Network Flow for Tracking Multiple People. PAMI (2013)Google Scholar
  4. 4.
    Benfold, B., Reid, I.: Stable multi-target tracking in real-time surveillance video. In: CVPR (2011)Google Scholar
  5. 5.
    Berclaz, J., Turetken, E., Fleuret, F., Fua, P.: Multiple Object Tracking using K-Shortest Paths Optimization. PAMI 33(9), 1806–1819 (2011)CrossRefGoogle Scholar
  6. 6.
    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)Google Scholar
  7. 7.
    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)Google Scholar
  8. 8.
    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)CrossRefGoogle Scholar
  9. 9.
    Brendel, W., Amer, M., Todorovic, S.: Multiobject tracking as maximum weight independent set. In: CVPR (2011)Google Scholar
  10. 10.
    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)CrossRefGoogle Scholar
  11. 11.
    Collins, R.: Multitarget data association with higher-order motion models. In: CVPR (2012)Google Scholar
  12. 12.
    Fleuret, F., Berclaz, J., Lengagne, R., Fua, P.: Multi-Camera People Tracking with a Probabilistic Occupancy Map. PAMI 30(2), 267–282 (2008)CrossRefGoogle Scholar
  13. 13.
    Ge, W., Collins, R.: Marked point processes for crowd counting. In: CVPR. pp. 2913–2920 (2009)Google Scholar
  14. 14.
    Ge, W., Collins, R.: Multi-target data association by tracklets with unsupervised parameter estimation. In: BMVC (2008)Google Scholar
  15. 15.
    Green, P.: Reversible jump markov chain monte carlo computation and bayesian model determination. Biometrika 82(4), 711–732 (1995)CrossRefzbMATHMathSciNetGoogle Scholar
  16. 16.
    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)CrossRefGoogle Scholar
  17. 17.
    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)CrossRefGoogle Scholar
  18. 18.
    Kim, W., Lee, K.: Markov chain monte carlo combined with deterministic methods for markov random field optimization. In: CVPR (2009)Google Scholar
  19. 19.
    Leibe, B., Schindler, K., Gool, L.J.V.: Coupled detection and trajectory estimation for multi-object tracking. In: ICCV, pp. 1–8 (2007)Google Scholar
  20. 20.
    van Lieshout, M.: Depth map calculation for a variable number of moving objects using markov sequential object processes. PAMI 30(7), 1308–1312 (2008)CrossRefGoogle Scholar
  21. 21.
    Milan, A., Roth, S., Schindler, K.: Continuous energy minimization for multitarget tracking. PAMI 36(1), 58–72 (2014)CrossRefGoogle Scholar
  22. 22.
    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)CrossRefMathSciNetGoogle Scholar
  23. 23.
    Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR (2011)Google Scholar
  24. 24.
    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)Google Scholar
  25. 25.
    Shafique, K., Shah, M.: A noniterative greedy algorithm for multiframe point correspondence. PAMI 27(1), 51–65 (2005)CrossRefGoogle Scholar
  26. 26.
    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)Google Scholar
  27. 27.
    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)CrossRefGoogle Scholar
  28. 28.
    Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: CVPR (2008)Google Scholar
  29. 29.
    Zhao, T., Nevatia, R.: Bayesian human segmentation in crowded situations. In: CVPR (2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Robert T. Collins
    • 1
  • Peter Carr
    • 2
  1. 1.The Pennsylvania State UniversityUSA
  2. 2.Disney Research PittsburghUSA

Personalised recommendations