Exploiting Crowd Synthesis for Multi-camera Human Tracking

Chapter

Abstract

There are many challenges to achieve a robust performance for tracking in a video network. In this chapter, we propose a method that integrates both detection and crowd synthesis approaches to achieve robust tracking performance. The experiments are conducted on PETS 2009 data set, and the performance is evaluated by multiple object tracking precision and accuracy criteria based on the position of each pedestrian on the ground plane. It is demonstrated that the information from crowd synthesis can provide significant advantage for tracking multiple pedestrians through multiple cameras.

References

  1. 1.
    Andriluka M, Roth S, Schiele B (2008) People-tracking-by-detection and people-detection-by-tracking. Comput Vis Pattern Recogn 2008:1–8Google Scholar
  2. 2.
    Babenko B, Yang M-H, Belongie S (2011) Robust object tracking with online multiple instance learning. IEEE Trans Pattern Anal Mach Intell 33(8):1619–1632CrossRefGoogle Scholar
  3. 3.
    Bernardin K, Stiefelhagen R (2008) Evaluating multiple object tracking performance: the clear mot metrics. J Image Video Process 2008:1:1–1:10Google Scholar
  4. 4.
    Breitenstein MD, Reichlin F, Leibe B, Koller-Meier E, Van Gool L (2011) Online multiperson tracking-by-detection from a single, uncalibrated camera. IEEE Trans Pattern Anal Mach Intell 33(9):1820–1833CrossRefGoogle Scholar
  5. 5.
    Chen X, Qin Z, An L, Bhanu B (2014) An online learned elementary grouping model for multi-target tracking. IEEE conference on computer vision and pattern recognition (CPVR), pp 1242–1249Google Scholar
  6. 6.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol 01. IEEE Computer Society, Washington, DC, pp 886–893Google Scholar
  7. 7.
    Du W, Piater Justus (2007) Multi-camera people tracking by collaborative particle filters and principal axis-based integration. In: Proceedings of the 8th Asian conference on computer vision—volume part I, ACCV’07. Springer, Berlin, pp 365–374Google Scholar
  8. 8.
    Eshel R, Moses Y (2010) Tracking in a dense crowd using multiple cameras. Int J Comput Vis 88(1):129–143CrossRefGoogle Scholar
  9. 9.
    Grabner H, Bischof H (2006) On-line boosting and vision. In: Proceedings of the 2006 IEEE computer society conference on computer vision and pattern recognition, CVPR ’06, IEEE computer society, vol 1, Washington, DC, pp 260–267Google Scholar
  10. 10.
    Grabner H, Leistner C, Bischof H (2008) Semi-supervised on-line boosting for robust tracking. In: Proceedings of the 10th European conference on computer vision: part I, ECCV ’08. Springer, Berlin, pp 234–247Google Scholar
  11. 11.
    Helbing D, Farkas I, Vicsek T (2000) Simulating dynamical features of escape panic. Nature 407:487CrossRefGoogle Scholar
  12. 12.
    Jin Z, Bhanu B (2012) Single camera multi-person tracking based on crowd simulation. In: IEEE international conference on pattern recognition (ICPR), Nov 2012, pp 3660–3663Google Scholar
  13. 13.
    Jin Z, Bhanu B (2013) Optimizing crowd simulation based on real video data. In: IEEE international conference on image processing (ICIP), Sept 2013, pp 3186–3190Google Scholar
  14. 14.
    Leibe B, Leonardis A, Schiele B (2008) Robust object detection with interleaved categorization and segmentation. Int J Comput Vis 77(1–3):259–289CrossRefGoogle Scholar
  15. 15.
    Lian G, Lai J, Zheng W (2011) Spatial-temporal consistent labeling of tracked pedestrians across non-overlapping camera views. Pattern Recogn 44(5):1121–1136CrossRefMATHGoogle Scholar
  16. 16.
    Lienhart R, Maydt J (2002) An extended set of haar-like features for rapid object detection. In: IEEE international conference on image processing (ICIP) vol 1, pp I-900–I-903Google Scholar
  17. 17.
    Moussaïd M, Perozo N, Garnier S, Helbing D, Theraulaz G (2010) The walking behaviour of pedestrian social groups and its impact on crowd dynamics. PLoS ONE 5:e10047CrossRefGoogle Scholar
  18. 18.
    Ondřej J, Pettré J, Olivier A, Donikian S (2010) A synthetic-vision based steering approach for crowd simulation. In: ACM SIGGRAPH 2010 papers, SIGGRAPH ’10, ACM, New York, pp 123:1–123:9Google Scholar
  19. 19.
    Qin Z (2012) Improving multi-target tracking via social grouping. Comput Vis Pattern Recognit 2012:1972–1978Google Scholar
  20. 20.
    Treuille A, Cooper S, Popović Z (2006) Continuum crowds. In: ACM SIGGRAPH, pp 1160–1168Google Scholar
  21. 21.
    van den Berg J, Guy SJ, Lin MC, Manocha D (2009) Reciprocal n-body collision avoidance. In: 14th international symposium on robotics research, Sept 2009Google Scholar
  22. 22.
    Weiming H, Min H (2006) Principal axis-based correspondence between multiple cameras for people tracking. IEEE Trans Pattern Anal Mach Intell 28(4):663–671CrossRefGoogle Scholar
  23. 23.
    Zhang L, van der Maaten L (2014) Preserving structure in model-free tracking. IEEE Trans Pattern Anal Mach Intell 36(4):756–769CrossRefGoogle Scholar
  24. 24.
    Zheng W, Gong S, Xiang T (2009) Associating groups of people. In: Proceedings of BMVC, pp 23.1–23.11. doi:10.5244/C.23.23

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.The Center for Research in Intelligent SystemsUniversity of CaliforniaRiversideUSA

Personalised recommendations