Skip to main content
SpringerLink
Log in

Tracking human poses in various scales with accurate appearance

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Building a robust and fully automatic framework for human motion tracking in 2D images and videos remains a challenging task in computer vision due to cluttered backgrounds, self-occlusions, variations of body shape and complexities of human postures. In this paper we propose a robust framework for human motion tracking without motion priors. The proposed framework builds an accurate/uncontaminated specific appearance model and then tracks the target’s postures with this specific appearance model. The main contribution of this work is a novel process to build an accurate appearance model by identifying non-target pixels and removing them. In addition, for the goal of tracking in multiple scales, a novel strategy for scale evaluation and adjustment is proposed to adaptively change the scale values during the tracking process. Experiments show that the accurate specific appearance model outperforms existing work, and the proposed tracking system is able to successfully track challenging sequences with different appearances, motions, scales and angles of view.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Poppe R (2007) Vision-based human motion analysis: an overview. Comput Vis Image Underst 108(1C2), 4–18

  2. Zhou H, Hu H (2008) Human motion tracking for rehabilitationła survey. Biomed Signal Process Control 3(1):1–18

    Article  Google Scholar 

  3. Ramanan D, Forsyth DA, Zisserman A (2007) Tracking people by learning their appearance. Pattern analysis and machine intelligence. IEEE Trans 29(1):65–81

    Google Scholar 

  4. Okuma K, Taleghani A, De Freitas N, Little JJ, Lowe DG (2004) A boosted particle filter: multitarget detection and tracking in ECCV. Springer, Berlin, pp 28–39

  5. Lu Y, Li L, Peursum P (2012) Human pose tracking based on both generic and specific appearance models. ICARCV

  6. Lu Y, Li L, Peursum P (2012) Background suppression for building accurate appearance models in human motion tracking. DICTA

  7. Tian J, Li L, Liu W (2014) Multi-scale human pose tracking in 2D monocular images. J Comput Commun 2:78

    Article  Google Scholar 

  8. Sigal L, Balan AO, Black MJ (2010) Humaneva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int J Comput Vis 87(1):4–27

    Article  Google Scholar 

  9. Sidenbladh H, Black M, Sigal L (2002) Implicit probabilistic models of human motion for synthesis and tracking. ECCV, pp 784–800

  10. Sidenbladh H, Black M, Fleet D (2000) Stochastic tracking of 3D human figures using 2d image motion. ECCV, pp 702–718

  11. Fablet R, Black MJ (2002) Automatic detection and tracking of human motion with a view-based representation in ECCV. Springer, Berlin, pp 476–491

  12. Deutscher J, Blake A, Reid I (2000) Articulated body motion capture by annealed particle filtering in CVPR, vol 2. IEEE, pp 126–133

  13. Kaliamoorthi P, Kakarala R (2013) Parametric annealing: a stochastic search method for human pose tracking. Pattern Recognit 46(5), 1501–1510 [Online]. http://www.sciencedirect.com/science/article/pii/S0031320312004669

  14. Bai T, Li Y (2012) Robust visual tracking with structured sparse representation appearance model. Pattern Recognit 45(6):2390–2404

    Article  MathSciNet  MATH  Google Scholar 

  15. Sullivan J, Carlsson S (2002) Recognizing and tracking human action in ECCV. Springer, Berlin, pp 629–644

  16. Song Y, Feng X, Perona P (2000) Towards detection of human motion in CVPR, vol 1. IEEE, pp 810–817

  17. Viola P, Jones MJ, Snow D (2005) Detecting pedestrians using patterns of motion and appearance. Int J Comput Vis 63(2):153–161

    Article  Google Scholar 

  18. Ponce J, Forsyth D, Willow E-P, Antipolis-Méditerranée S (2011) R. d’activité RAweb, L. Inria, and I. Alumni. Comput vision: a modern approach. Computer 16:11

  19. Fischler MA, Elschlager RA (1973) The representation and matching of pictorial structures. Comput IEEE Trans 100(1):67–92

    Article  Google Scholar 

  20. Felzenszwalb PF, Huttenlocher DP (2005) Pictorial structures for object recognition. Int J Comput Vis 61(1):55–79

    Article  Google Scholar 

  21. Andriluka M, Roth S, Schiele B (2009) Pictorial structures revisited: people detection and articulated pose estimation in CVPR. IEEE, pp 1014–1021

  22. Andriluka M, Roth S, Schiele B (2012) Discriminative appearance models for pictorial structures. Int J Comput Vis 1–22

  23. Mori G, Ren X, Efros AA, Malik J (2004) Recovering human body configurations: combining segmentation and recognition in CVPR, vol 2. IEEE, pp II-326

  24. Ramanan D (2007) Learning to parse images of articulated bodies. Adv Neural Inf Process Syst 19:1129

    Google Scholar 

  25. Ferrari V, Marín-Jiménez M, Zisserman A (2009) 2D human pose estimation in tv shows. Stat Geometr Approach Vis Motion Anal 128–147

  26. Artner NM, Ion A, Kropatsch WG (2011) Reprint of: multi-scale 2d tracking of articulated objects using hierarchical spring systems. Pattern Recognit 44(9):1969–1979

    Article  Google Scholar 

  27. Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. Pattern Anal Mach Intell IEEE Trans 24(5):603–619

    Article  Google Scholar 

  28. Ferrari V, Marin-Jimenez M, Zisserman A (2008) Progressive search space reduction for human pose estimation in CVPR 2008. IEEE Conference on. IEEE, pp 1–8

Download references

Author information

Authors and Affiliations

  1. Department of Computing, Curtin University, Perth, Western Australia

    Jinglan Tian, Yao Lu, Ling Li & Wanquan Liu

Authors
  1. Jinglan Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yao Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ling Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wanquan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wanquan Liu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tian, J., Lu, Y., Li, L. et al. Tracking human poses in various scales with accurate appearance. Int. J. Mach. Learn. & Cyber. 8, 1667–1680 (2017). https://doi.org/10.1007/s13042-016-0537-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-016-0537-8

Keywords

Search

Navigation