Pattern Analysis and Applications

, Volume 15, Issue 4, pp 399–413 | Cite as

Human body segmentation based on deformable models and two-scale superpixel

  • Shifeng Li
  • Hu-Chuan LuEmail author
  • Xiang Ruan
  • Yen-Wei Chen
Theoretical Advances


In this paper, we propose a novel method to segment human body in static images by graph cuts based on two deformable models at two-scale superpixel. In our study, body segmentation is decomposed into torso detection and lower body recovery. Based on the first-scale superpixel, the seeds of torso are obtained on the basis of the coarse torso region, which is estimated by an improved deformable torso model. For the lower body, we estimate the hip region to obtain the seeds of lower body at the second-scale superpixel. Besides, a deformable upper leg model is designed to derive more foreground seeds of the lower body. To avoid failure caused by the heavy dependence between the two hierarchies, a scheme of probabilistic hierarchical detection is presented. Experiments on our datasets containing 200 images photographed by ourselves and 100 other images collected from public datasets show that our approach can accurately segment human body in static images with a variety of poses, backgrounds and clothing. Segmenting the human body in static image based on deformable torso and upper leg models at two-scale superpixel.


Body segmentation Superpixel Deformable model Graph cuts 



The work was supported by the Fundamental Research Funds for the Central Universities, No. DUT10JS05, the National Natural Science Foundation of China (NSFC), No. 61071209 and Omron Corporation's grant No. DUT09001.

Supplementary material

10044_2011_220_MOESM1_ESM.doc (853 kb)
Supplementary material 1 (DOC 853 kb)


  1. 1.
    Boykov Y, Veksler O, Zabih R (2001) Fast approximate energy minimisation via graph cuts. IEEE Trans PAMI 23(11):1222–1239CrossRefGoogle Scholar
  2. 2.
    Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans PAMI 22(8):888–905CrossRefGoogle Scholar
  3. 3.
    Mori G, Malik J (2002) Estimating human body configurations using shape context matching. In: European conference on computer vision. LNCS 2352, 666–680Google Scholar
  4. 4.
    Poppe R, Poel M (2005) Example-based pose estimation in monocular images using compact fourier descriptors. Technical report TR-CTIT-05-49, pp 1–19Google Scholar
  5. 5.
    Agarwal A, Triggs B (2006) A local basis representation for estimating human pose from cluttered images. ACCV, pp 50–59Google Scholar
  6. 6.
    Lin Z, Davis LS, Doermann D, DeMenthon D (2007) Hierarchical Part-Template Matching for Human Detection and Segmentation, ICCVGoogle Scholar
  7. 7.
    Mohan A, Papageorgiou C, Poggio T (2001) Example-based object detection in images by components. IEEE Trans PAMI 23(4):349–361CrossRefGoogle Scholar
  8. 8.
    Mori G, Ren X, Efros AA, Malik J (2004) Recovering human body configurations: combining segmentation and recognition. CVPR, pp 326–333Google Scholar
  9. 9.
    Hu Z, Lin X, Yan H (2006) Torso Detection in Static Images. ICSPGoogle Scholar
  10. 10.
    Strinivasan P, Shi J (2007) Bottom-up recognition and parsing of the human body. CVPRGoogle Scholar
  11. 11.
    Ramanan D, Forsyth DA (2003) Finding and tracking people from the bottom up. CVPRGoogle Scholar
  12. 12.
    Lee MW, Cohen I (2004) Human upper body pose estimation in static images. ECCVGoogle Scholar
  13. 13.
    Ramanan D, Sminchisescu C (2006) Training deformable models for localization. CVPR, 206–213Google Scholar
  14. 14.
    Mori G (2005) Guiding model search using segmentation. ICCV, pp 1417–1423Google Scholar
  15. 15.
    Lee MW, Nevatia R (2007) Body part detection for human pose estimation and tracking. IEEE WMVC, pp 23–31Google Scholar
  16. 16.
    Hu Z, Wang G, Lin X, yan H (2009) Recovery of upper body poses in static images based on joints detection. Pattern Recog Lett 30(5):503–512CrossRefGoogle Scholar
  17. 17.
    Fulkerson B, Vedaldi A, Soatto S (2009) Class segmentation and object localization with superpixel neighborhoods. ICCV, pp 670–678Google Scholar
  18. 18.
    Ren X, Malik J (2003) Learning a classification model for segmentation. ICCV, pp 10–17Google Scholar
  19. 19.
    Oliveira PR, Romero RAF (2008) Improvements on ICA mixture models for image pre-processing and segmentation. Neurocomputing 71(10-12):2180–2193CrossRefGoogle Scholar
  20. 20.
    Maire M, Arbelaez P, Fowlkes C, Malik J (2008) Using contours to detect and localize junctions in natural images. CVPR, pp 1–8Google Scholar
  21. 21.
    Viola P, Jones M (2004) Robust real-time face detection. Int J Comput Vis 57(2):137–154CrossRefGoogle Scholar
  22. 22.
    Rother C, Kolmogorov V, Blake A (2004) Grabcut: interactive foreground extraction using iterated graph cuts. ACM Trans Graph 23(3):309–314CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  • Shifeng Li
    • 1
  • Hu-Chuan Lu
    • 1
    Email author
  • Xiang Ruan
    • 2
  • Yen-Wei Chen
    • 3
  1. 1.Department of Electronic EngineeringDalian University of TechnologyDalianChina
  2. 2.Digtial Imaging and Mobile Devices Department Image Processing Design SectionOmronKyotoJapan
  3. 3.College of Information Science and Engineering, Ritsumeikan UniversityKusatsuJapan

Personalised recommendations