A Pose-Invariant Descriptor for Human Detection and Segmentation

  • Zhe Lin
  • Larry S. Davis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5305)


We present a learning-based, sliding window-style approach for the problem of detecting humans in still images. Instead of traditional concatenation-style image location-based feature encoding, a global descriptor more invariant to pose variation is introduced. Specifically, we propose a principled approach to learning and classifying human/non-human image patterns by simultaneously segmenting human shapes and poses, and extracting articulation-insensitive features. The shapes and poses are segmented by an efficient, probabilistic hierarchical part-template matching algorithm, and the features are collected in the context of poses by tracing around the estimated shape boundaries. Histograms of oriented gradients are used as a source of low-level features from which our pose-invariant descriptors are computed, and kernel SVMs are adopted as the test classifiers. We evaluate our detection and segmentation approach on two public pedestrian datasets.


Object Detection Image Patch Contour Point Human Detection Edge Orientation 
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.


  1. 1.
    Gavrila, D.M., Philomin, V.: Real-time object detection for smart vehicles. In: ICCV (1999)Google Scholar
  2. 2.
    Papageorgiou, C., Evgeniou, T., Poggio, T.: A trainable pedestrian detection syste. In: Proc. of Intelligent Vehicles (1998)Google Scholar
  3. 3.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)Google Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  5. 5.
    Wu, Y., Yu, T., Hua, G.: A statistical field model for pedestrian detection. In: CVPR (2005)Google Scholar
  6. 6.
    Tuzel, O., Porikli, F., Meer, P.: Human detection via classification on riemannian manifold. In: CVPR (2007)Google Scholar
  7. 7.
    Mikolajczyk, K., Schmid, C., Zisserman, A.: Human detection based on a probabilistic assembly of robust part detectors. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 69–82. Springer, Heidelberg (2004)Google Scholar
  8. 8.
    Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: CVPR (2005)Google Scholar
  9. 9.
    Shotton, J., Blake, A., Cipolla, R.: Contour-based learning for object detection. In: ICCV (2005)Google Scholar
  10. 10.
    Opelt, A., Pinz, A., Zisserman, A.: A boundary-fragment-model for object detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 575–588. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. IEEE Trans. PAMI 30(1), 36–51 (2008)Google Scholar
  12. 12.
    Wu, B., Nevatia, R.: Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In: ICCV (2005)Google Scholar
  13. 13.
    Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. IEEE Trans. PAMI 23(4), 349–361 (2001)Google Scholar
  14. 14.
    Lin, Z., Davis, L.S., Doermann, D., DeMenthon, D.: Hierarchical part-template matching for human detection and segmentation. In: ICCV (2007)Google Scholar
  15. 15.
    Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: ICCV (2003)Google Scholar
  16. 16.
    Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 428–441. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  17. 17.
    Sharma, V., Davis, J.W.: Integrating appearance and motion cues for simultaneous detection and segmentation of pedestrians. In: ICCV (2007)Google Scholar
  18. 18.
    Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T.: Fast human detection using a cascade of histograms of oriented gradients. In: CVPR (2006)Google Scholar
  19. 19.
    Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: CVPR (2008)Google Scholar
  20. 20.
    Sabzmeydani, P., Mori, G.: Detecting pedestrians by learning shapelet features. In: CVPR (2007)Google Scholar
  21. 21.
    Wu, B., Nevatia, R.: Optimizing discrimination-efficientcy tradeoff in integrating heterogeneous local features for object detection. In: CVPR (2008)Google Scholar
  22. 22.
    Gavrila, D.M.: A bayesian, exemplar-based approach to hierarchical shape matching. IEEE Trans. PAMI 29(8), 1408–1421 (2007)Google Scholar
  23. 23.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial Structures for Object Recognition. International Journal of Computer Vision 61(1), 55–79 (2005)CrossRefGoogle Scholar
  24. 24.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines (2001),

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Zhe Lin
    • 1
  • Larry S. Davis
    • 1
  1. 1.Institute of Advanced Computer StudiesUniversity of MarylandCollege Park 

Personalised recommendations