Human Relative Position Detection Based on Mutual Occlusion

  • Víctor Borjas
  • Michal Drozdzal
  • Petia Radeva
  • Jordi Vitrià
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7441)

Abstract

In this paper, we propose, within the field of automatic social context analysis, a novel method to identify the mutual position between two persons in images. Based on the idea that mutual information of head position, body visibility and bodies’ contour shapes may lead to a good estimation of mutual position between people, a predictor is constructed to classify the relative position between both subjects. We advocate the use of superpixels as the basic unit of the human analysis framework. We construct a Support Vector Machine classifier on the feature vector for each image. The results show that this combination of features, provides a significantly low error rate with low variance in our database of 366 images.

Keywords

Gaussian Mixture Model Mutual Position Head Detection Skin Detection Skin Pixel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Sivic, J., Zitnick, C., Szeliski, R.: Finding people in repeated shots of the same scene. In: Proc. BMVC (2006)Google Scholar
  2. 2.
    Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: TurboPixels: Fast Superpixels Using Geometric Flows. TPAMI (2009)Google Scholar
  3. 3.
    Gomez, G., Morales, E.F.: Automatic feature construction and a simple rule induction algorithm for skin detection. In: Proc. ICML Workshop on Machine Learning in Computer VisionGoogle Scholar
  4. 4.
    Gallagher, A., Chen, T.: Clothing cosegmentation for recognizing people. In: Proc. CVPR (2008)Google Scholar
  5. 5.
    Gallagher, A., Chen, T.: Using group prior to identify people in consumer images. In: Proc. CVPR SLAM Workshop (2007)Google Scholar
  6. 6.
    Gallagher, A., Chen, T.: Understanding Images of Groups of People. In: Proc. CVPR (2009)Google Scholar
  7. 7.
    Naaman, M., Yeh, R., Garcia-Molina, H., Paepcke, A.: Leveraging context to resolve identity in photo albums. In: Proc. JCDL (2005)Google Scholar
  8. 8.
    Stone, Z., Zickler, T., Darrell, T.: Autotagging facebook: Social network context improves photo annotation. In: Proc. CVPR, Internet Vision Workshop (2008)Google Scholar
  9. 9.
    Drozdzal, M., Hernández, A., Segu, S., Baro, X., Escalera, S., Lapedriza, A., Masip, D., Radeva, P., Vitria, J.: Combining Detectors for Human Layout Analysis. In: Proc. ECCV, The Pascal Visual Object Classes Challenge Workshop (2010)Google Scholar
  10. 10.
    Vezhnevets, V., Sazonov, V., Andreeva, A.: A Survey on Pixel-Based Skin Color Detection Techniques. In: Proc. GRAPHICON (2003)Google Scholar
  11. 11.
    Rother, C., Kolmogorov, V., Blake, A.: GrabCut, interactive foreground extraction using iterated graph cuts. ACM Trans. SIGGRAPH (2004)Google Scholar
  12. 12.
    Fulkerson, B., Vedaldi, A., Soatto, S.: Class segmentation and object localization with superpixel neighborhoods. In: Proc. ICCV (2009)Google Scholar
  13. 13.
    Boykov, Y., Jolly, M.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: Proc. ICCV (2001)Google Scholar
  14. 14.
    Ruzon, M., Tomasi, C.: Alpha estimation in natural images. In: Proc. CVPR (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Víctor Borjas
    • 1
  • Michal Drozdzal
    • 1
  • Petia Radeva
    • 1
  • Jordi Vitrià
    • 1
  1. 1.Facultat de Matemàtiques & Centre de Visiò per ComputadorUniversitat de BarcelonaSpain

Personalised recommendations