Multimedia Tools and Applications

, Volume 76, Issue 5, pp 6731–6754 | Cite as

Multi-human tracking using part-based appearance modelling and grouping-based tracklet association for visual surveillance applications

Article

Abstract

Although much progress has been made in multi-object tracking in recent decades due to its variety of applications including visual surveillance, traffic monitoring and medical image analysis, some difficult challenges such as the variation of object appearance and partial occlusion are still going on. In this work, we propose an effective multi-human tracking system called part-based appearance modelling and grouping-based tracklet association-based multi-human tracking (PAM-GTA-MHT). The proposed appearance model based on the upper body-centered multi-view human body part model can effectively resolve the drawback caused by inter-object occlusions and low camera positions. The grouping method embedded in global tracklet association can improve discriminability among targets with similar appearances when they are located sufficiently far away from each other. Thus, there is no need to compare all possible pairs of the detected targets in the tracklet association stage and thus it has the potential to enhance the tracking speed. We quantitatively evaluated the performance of our proposed approach on four challenging publicly available datasets and achieved a significant improvement compared to the state-of-the-art methods.

Keywords

Multi-human tracking Part-based appearance model Grouping-based tracklet association Data association 

References

  1. 1.
    Andriluka M, Roth S, Schiele B et al. (2008) People-tracking-by detection and people-detection-by-tracking. Proc IEEE Conf Comput Vision Pattern Recognit 1–8Google Scholar
  2. 2.
    Andriyenko A, Roth S, Schindler K et al. (2011) An analytical formulation of global occlusion reasoning for multi-target tracking. 2011 I.E. Int Conf ICCV Workshops 1839–1846Google Scholar
  3. 3.
    Andriyenko A, Schindler K (2010) Globally optimal multi-target tracking on a hexagonal lattices. Proc 11th Europ Conf Comput Vision 466–479Google Scholar
  4. 4.
    Andriyenko A, Schindler K (2011) Multi-target tracking by continuous energy minimization. Proc IEEE Conf Comput Vision Pattern Recognit 1265–1272Google Scholar
  5. 5.
    Avidan S (2007) Ensemble tracking. IEEE Trans Pattern Anal Mach Intell 29(2):261–271CrossRefGoogle Scholar
  6. 6.
    Berclaz J, Fleuret F, Fua P (2006) Robust people tracking with global trajectory optimization. Proc IEEE Conf Comput Vision Pattern Recognit 1:744–750Google Scholar
  7. 7.
    Birchfield S-T, Rangarajan S (2005) Spatiograms versus histograms for region-based tracking. Proc IEEE Conf Comput Vision Pattern Recognit 2:1158–1163Google Scholar
  8. 8.
    Breitenstein M-D, Reichlin F, Leibe B et al. (2009) Robust tracking-by-detection using a detector confidence particle filter. Proc IEEE Int Conf Comput Vision 1515–1522Google Scholar
  9. 9.
    Brendel W, Amer M, Todorovic S ET A et al. (2011) Multiobject tracking as maximum weight independent set. Proc IEEE Conf Comput Vision Pattern Recognit 1273–1280Google Scholar
  10. 10.
    Cai Y, de Freitas N, Little J-J (2006) Robust visual tracking for multiple targets. Pro 9th Europ Conf Comput Vision 3954:107–118Google Scholar
  11. 11.
    Cannons K-J, Gryn J-M, Wildes R-P (2010) Visual tracking using a pixelwise spatiotemporal oriented energy representation. Proc 11th Europ Conf Comput Vision 6314:511–524Google Scholar
  12. 12.
  13. 13.
    Collins R-T, Liu Y (2005) On-line selection of discriminative tracking features. IEEE Trans Pattern Anal Mach Intell 27(10):1631–1643CrossRefGoogle Scholar
  14. 14.
    Dalal N; Triggs B (2005) Histograms of oriented gradients for human detection. Proc IEEE Conf Comput Vision Pattern Recognit 886–893Google Scholar
  15. 15.
    Ess A, Leibe B, Schindler K et al. (2008) A mobile vision system for robust multi-person tracking. Proc IEEE Conf Comput Vision Pattern Recognit 1–8Google Scholar
  16. 16.
    Farenzena M, Bazzani L, Perina1 A et al. (2010) Person re-identification by symmetry-driven accumulation of local features. Proc IEEE Conf Comput Vision Pattern Recognit 2360–2367Google Scholar
  17. 17.
    Felzenszwalb P, Girshick R, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645CrossRefGoogle Scholar
  18. 18.
    Fulkerson B, Vedaldi A, Soatto S (2008) Localizing objects with smart dictionaries. Proc 9th Europ Conf Comput Vision 5302:179–192Google Scholar
  19. 19.
    Grabner H, Bischof H (2006) On-line boosting and vision. Proc IEEE Conf Comput Vision Pattern Recognit 1:260–267Google Scholar
  20. 20.
    Grabner H, Matas J, Gool L V et al. (2010) Tracking the invisible: learning where the object might be. Proc IEEE Conf Comput Vision Pattern Recognit 1285–1292Google Scholar
  21. 21.
    Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. Proc 10th Europ Conf Comput Vision 262–275Google Scholar
  22. 22.
    Heili A, Chen C, Odobez J-M et al. (2011) Detection-based multi-human tracking using a CRF model. Proc IEEE Int Conf Comput Vision Workshop 1673–1680Google Scholar
  23. 23.
    Hou C, Ai H, Lao S (2007) Multiview pedestrian detection based on vector boosting. Proc 6th Asian Conf Comput Vision 4843:210–219Google Scholar
  24. 24.
    Huang C, Wu B, Nevatia R (2008) Robust object tracking by hierarchical association of detection responses. Proc 10th Europ Conf Comput Vision 5305:788–801Google Scholar
  25. 25.
    Jiang H, Fels S, Little J-J et al. (2007) A linear programming approach for multiple object tracking. Proc IEEE Conf Comput Vision Pattern Recognit 1–8Google Scholar
  26. 26.
    Kim S, Kwak S, Feyereisl J, Han B (2012) Online multi-target tracking by large margin structured learning. Proc 11th Asian Conf Comput Vision 7726:98–111Google Scholar
  27. 27.
    Kuo C-H, Huang C, Nevatia R et al. (2010) Multi-target tracking by online learned discriminative appearance models. Proc IEEE Conf Comput Vision Pattern Recognit 685–692Google Scholar
  28. 28.
    Kuo C-H., Nevatia R (2011) How does person identity recognition help multi-person tracking?. Proc IEEE Conf Comput Vision Pattern Recognit 1217–1224Google Scholar
  29. 29.
    Leibe B, Leonardis A, Schiele B (2008) Robust object detection with interleaved categorization and segmentation. Int J Comput Vis 77:259–289CrossRefGoogle Scholar
  30. 30.
    Leibe B, Schindler K, Gool L-V et al. (2007) Coupled detection and trajectory estimation for multi-object tracking. Proc IEEE Int Conf Comput Vision 1–8Google Scholar
  31. 31.
    Levi K, Weiss Y (2004) Learning object detection from a small number of examples: the importance of good features. Proc IEEE Conf Comput Vision Pattern Recognit 2:53–60Google Scholar
  32. 32.
    Li Y, Ai H, Yamashita T, Lao S, Kawade M (2008) Tracking in low frame rate video: a cascade particle filter with discriminative observers of different lifespans. IEEE Trans Pattern Anal Mach Intell 30(10):1728–1740CrossRefGoogle Scholar
  33. 33.
    Li Y, Huang C, Nevatia R et al. (2009) Learning to associate: hybridboosted multi-target tracker for crowded scene. Proc IEEE Conf Comput Vision Pattern Recognit 2953–2960Google Scholar
  34. 34.
    Lowe D-G (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  35. 35.
    Okuma K, Taleghani A, Freitas OD, Little J-J, Lowe D-G (2004) A boosted particle filter: Multitarget detection and tracking. Proc 8th Europ Conf Comput Vision 3021:28–39MATHGoogle Scholar
  36. 36.
    Perera AGA, Srinivas C, Hoogs A, Brooksby G, Hu W (2006) Multi-object tracking through simultaneous long occlusions and split-merge conditions. Proc IEEE Conf Comput Vision Pattern Recognit 1:666–673Google Scholar
  37. 37.
  38. 38.
    Pirsiavash H, Ramanan D, Fowlkes C et al. (2011) Globally-optimal greedy algorithms for tracking a variable number of objects. Proc IEEE Conf Comput Vision Pattern Recognit 1201–1208Google Scholar
  39. 39.
    Song B, Jeng T-Y, Staudt E, Roy-Chowdhury A-K (2010) A stochastic graph evolution framework for robust multi-target tracking. Proc 11th Europ Conf Comput Vision 6311:05–619Google Scholar
  40. 40.
    Tsochantaridis I, Hofmann T, Joachims T et al. (2004) Support vector machine learning for interdependent and structured output space. Int Conf Mach Learn 104–112Google Scholar
  41. 41.
    Tuzel O, Porikli F, Meer P et al. (2007) Human detection via classification on riemannian manifolds. Proc IEEE Conf Comput Vision Pattern Recognit 1–8Google Scholar
  42. 42.
    Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. ProcIEEE Conf ComputVision Pattern Recognit 1:511–518Google Scholar
  43. 43.
    Walk S, Majer N, Schindler K et al. (2010) New features and insights for pedestrian detection. Proc IEEE Conf Comput Vision Pattern Recognit 1030–1037Google Scholar
  44. 44.
    Wang X, Han TX., Yan S et al. (2009) An hog-lbp human detector with partial occlusion handling. Proc IEEE Int Conf Comput Vision 32–29Google Scholar
  45. 45.
    Wu B, Nevatia R (2005) Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors. Proc IEEE Conf Computer Vision Pattern Recognit 1:90–97Google Scholar
  46. 46.
    Wu B, Nevatia R (2007) Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors. Int J Comput Vis 75(2):247–266CrossRefGoogle Scholar
  47. 47.
    Xing J, Ai H, Lao S et al. (2009) Multi-object tracking through occlusions by local tracklets filtering and global tracklets association with detection responses. Proc IEEE Conf Comput Vision Pattern Recognit 1200–1207Google Scholar
  48. 48.
    Yang B, Huang C, Nevatia R et al. (2011) Learning affinities and dependencies for multi-target tracking using a CRF model. Proc IEEE Conf Comput Vision Pattern Recognit 1233–1240Google Scholar
  49. 49.
    Yang M, Lv F, Xu W et al. (2009) Detection driven adaptive multi-cue integration for multiple human tracking. Proc IEEE Int Conf Comput Vision 1554–1561Google Scholar
  50. 50.
    Yang B, Nevatia R (2012) Multi-target tracking by online learning of non-linear motion patterns and robust appearance models. Proc IEEE Conf Comput Vision Pattern Recognit 1918–1925Google Scholar
  51. 51.
    Yang B, Nevatia R (2012) An online learned CRF model for multi-target tracking. Proc IEEE Conf Comput Vision Pattern Recognit 2034–2041Google Scholar
  52. 52.
    Yu Q, Medioni G (2009) Multiple-target tracking by spatiotemporal monte carlo markov chain data association. IEEE Trans Pattern Anal Mach Intell 31(12):2196–2210CrossRefGoogle Scholar
  53. 53.
    Zhang L, Li Y, Nevatia R et al. (2008) Global data association for multi-object tracking using network flows. Proc IEEE Conf Comput Vision Pattern Recognit 1–8Google Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.School of Information and CommunicationsGwangju Institute of Science and TechnologyGwangjuSouth Korea

Personalised recommendations