Tracklet Reidentification in Crowded Scenes Using Bag of Spatio-temporal Histograms of Oriented Gradients

  • Michał Lewandowski
  • Damien Simonnet
  • Dimitrios Makris
  • Sergio A. Velastin
  • James Orwell
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7914)

Abstract

A novel tracklet association framework is introduced to perform robust online re-identification of pedestrians in crowded scenes recorded by a single camera. Recent advances in multi-target tracking allow the generation of longer tracks, but problems of fragmentation and identity switching remain, due to occlusions and interactions between subjects. To address these issues, a discriminative and efficient descriptor is proposed to represent a tracklet as a bag of independent motion signatures using spatio-temporal histograms of oriented gradients. Due to the significant temporal variations of these features, they are generated only at automatically identified key poses that capture the essence of its appearance and motion. As a consequence, the re-identification involves only the most appropriate features in the bag at given time. The superiority of the methodology is demonstrated on two publicly available datasets achieving accuracy over 90% of the first rank tracklet associations.

Keywords

multi-target tracking tracklet association visual surveillance histogram of oriented gradients computer vision 

References

  1. 1.
    Andriyenko, A., Schindler, K.: Multi-target tracking by continuous energy minimization. In: Proc. of CVPR (2011)Google Scholar
  2. 2.
    Benfold, B., Reid, I.: Stable Multi-Target tracking in Real-Time surveillance video. In: Proc. of CVPR (2011)Google Scholar
  3. 3.
    Cutler, R., Davis, L.S.: Robust Real-Time periodic motion detection, analysis, and applications. TPAMI (2000)Google Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. of CVPR (2005)Google Scholar
  5. 5.
    Kläser, A., Marszałek, M., Schmid, C.: A Spatio-Temporal descriptor based on 3D-gradients. In: Proc. of BMVC (2008)Google Scholar
  6. 6.
    Kuo, C.-H., Nevatia, R.: How does person identity recognition help Multi-Person tracking? In: Proc. of CVPR (2011)Google Scholar
  7. 7.
    Lele, S.: Euclidean distance matrix analysis (edma): Estimation of mean form and mean form difference. In: Mathematical Geology (1993)Google Scholar
  8. 8.
    Schütze, T., Schwetlick, H.: Constrained approximation by splines with free knots. In: BIT Numerical Mathematics (1997)Google Scholar
  9. 9.
    Simonnet, D., Lewandowski, M., Velastin, S., Orwell, J., Turkbeyler, E.: Tracking pedestrians in crowded scenes using dynamic time-warped appearance features. In: Workshop PCRA (2012)Google Scholar
  10. 10.
    Song, B., Jeng, T.-Y., Staudt, E., Roy-Chowdhury, A.K.: A stochastic graph evolution framework for robust multi-target tracking. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 605–619. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  11. 11.
    Song, X., Shao, X., Zhao, H., Cui, J., Shibasaki, R., Zha, H.: An online approach: Learning-semantic-scene-by-tracking and tracking-by-learning-semantic-scene. In: Proc. of CVPR (2010)Google Scholar
  12. 12.
    Kim, S., Kwak, S., Feyereisl, J., Han, B.: Online multi-target tracking by large margin structured learning. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part III. LNCS, vol. 7726, pp. 98–111. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  13. 13.
    Welch, G., Bishop, G.: An introduction to the kalman filter (1995)Google Scholar
  14. 14.
    Wiener, N.: Generalized harmonic analysis. Acta Mathematica (1930)Google Scholar
  15. 15.
    Yang, B., Nevatia, R.: Multi-target tracking by online learning of non-linear motion patterns and robust appearance models. In: Proc. of CVPR (2012)Google Scholar
  16. 16.
    Yang, B., Huang, C., Nevatia, R.: Learning affinities and dependencies for multi-target tracking using a crf model. In: Proc. of CVPR (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Michał Lewandowski
    • 1
  • Damien Simonnet
    • 1
  • Dimitrios Makris
    • 1
  • Sergio A. Velastin
    • 1
    • 2
  • James Orwell
    • 1
  1. 1.Digital Imaging Research CentreKingston UniversityUK
  2. 2.Department of Informatic EngineeringUniversidad de Santiago de ChileChile

Personalised recommendations