Pedestrian Image Segmentation via Shape-Prior Constrained Random Walks

  • Ke-Chun Li
  • Hong-Ren Su
  • Shang-Hong Lai
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7088)

Abstract

In this paper, we present an automatic and accurate pedestrian segmentation algorithm by incorporating pedestrian shape prior into the random walks segmentation algorithm. The random walks [1] algorithm requires user-specified labels to produce segmentation with each pixel assigned to a label, and it can provide satisfactory segmentation result with proper input labeled seeds. To take advantage of this interactive segmentation algorithm, we improve the random walks segmentation algorithm by incorporating prior shape information into the same optimization formulation. By using the human shape prior, we develop a fully automatic pedestrian image segmentation algorithm. Our experimental results demonstrate that the proposed algorithm significantly outperforms the previous segmentation methods in terms of pedestrian segmentation accuracy on a number of real images.

Keywords

human segmentation random walks shape prior 

References

  1. 1.
    Grady, L.: Random Walks for Image Segmentation Journal. IEEE Trans. Pattern Analysis and Machine Intelligence 28(11), 1768–1783 (2006)CrossRefGoogle Scholar
  2. 2.
    Juan, C.-F., Chang, C.-M., Wu, J.-R., Lee, D.: Computer Vision-Based Human Body Segmentation and Posture Estimation. IEEE Trans. Systems, Man and Cybernetics, Part A: Systems and Humans 39(1), 119–133 (2009)CrossRefGoogle Scholar
  3. 3.
    Cucchiara, R., Grana, C., Prati, A., Vezzani, R.: Probabilistic posture classification for Human-behavior analysis. IEEE Trans. Systems, Man and Cybernetics, Part A: Systems and Humans 35(1), 42–54 (2005)CrossRefGoogle Scholar
  4. 4.
    Lin, Z., Davis, L.S.: Shape-Based Human Detection and Segmentation via Hierarchical Part-Template Matching. IEEE Trans. Pattern Analysis and Machine Intelligence 32(4), 604–618 (2010)CrossRefGoogle Scholar
  5. 5.
    Lin, Z., Davis, L.S., Doermann, D., DeMenthon, D.: Hierarchical Part-Template Matching for Human Detection and Segmentation. In: International Conf. on Computer Vision, pp. 1–8 (2007)Google Scholar
  6. 6.
    Gao, W., Ai, H., Lao, S.: Adaptive Contour Features in oriented granular space for human detection and segmentation. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1786–1793 (2009)Google Scholar
  7. 7.
    Viola, P., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: International Conf. on Computer Vision, vol. 2, pp. 734–741 (2003)Google Scholar
  8. 8.
    Schapire, R., Singer, Y.: Improved Boosting Algorithms Using Confidence-rated Predictions. Machine Learning 37, 297–336 (1999)CrossRefMATHGoogle Scholar
  9. 9.
    Givoni, I.E., Frey, B.J.: A Binary Variable Model for Affinity Propagation. Neural Computation 21, 1589–1600 (2009)MathSciNetCrossRefMATHGoogle Scholar
  10. 10.
    Kim, T.H., Lee, K.M., Lee, S.U.: Nonparametric higher-order learning for interactive segmentation. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 32201–3208 (2010)Google Scholar
  11. 11.
    Courant, R., Hilbert, D.: Methods of Math. Physics, vol. 2. John Wiley and Sons (1989)Google Scholar
  12. 12.
    Merris, R.: Laplacian Matrices of Graphs: A Survey. Linear Algebra and Its Applications 197,198, 143–176 (1994)MathSciNetCrossRefMATHGoogle Scholar
  13. 13.
    Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  14. 14.
  15. 15.
  16. 16.
  17. 17.
  18. 18.
    Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  19. 19.
    Wu, B., Nevatia, R.: Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar
  20. 20.
    Rother, C., Kolmogorov, V., Blake, A.: Interactive Foreground Extraction using Iterated Graph Cuts. ACM Trans. on Graphics 23, 309–314 (2004)CrossRefGoogle Scholar
  21. 21.
    Grady, L.: Multilabel Random Walker Image Segmentation Using Prior Models. In: IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 763–770 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Ke-Chun Li
    • 1
  • Hong-Ren Su
    • 1
  • Shang-Hong Lai
    • 1
  1. 1.Department of Computer ScienceNational Tsing Hua UniversityHsinchuTaiwan

Personalised recommendations