Human Detection Based on a Probabilistic Assembly of Robust Part Detectors

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3021)


We describe a novel method for human detection in single images which can detect full bodies as well as close-up views in the presence of clutter and occlusion. Humans are modeled as flexible assemblies of parts, and robust part detection is the key to the approach. The parts are represented by co-occurrences of local features which captures the spatial layout of the part’s appearance. Feature selection and the part detectors are learnt from training images using AdaBoost.

The detection algorithm is very efficient as (i) all part detectors use the same initial features, (ii) a coarse-to-fine cascade approach is used for part detection, (iii) a part assembly strategy reduces the number of spurious detections and the search space. The results outperform existing human detectors.


Body Part Face Detection Human Detection Dominant Orientation Part Detector 
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.
    Felzenszwalb, P.: Learning models for object recognition. In: Proc. of the CVPR, Hawaii, USA, pp. 1056–1062 (2001) Google Scholar
  2. 2.
    Felzenszwalb, P., Huttenlocher, D.: Efficient matching of pictorial structures. In: Proc. of the CVPR, Hilton Head Island, USA, pp. 66–75 (2000) Google Scholar
  3. 3.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. of the CVPR, Madison, USA, pp. 264–271 (2003) Google Scholar
  4. 4.
    Forsyth, D., Fleck, M.: Body plans. In: Proc. of the CVPR, Puerto Rico, USA, pp. 678–683 (1997) Google Scholar
  5. 5.
    Gavrila, D.M.: Pedestrian detection from a moving vehicle. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 37–49. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  6. 6.
    Ioffe, S., Forsyth, D.: Probabilistic methods for finding people. International Journal of Computer Vision 43(1), 45–68 (2001)zbMATHCrossRefGoogle Scholar
  7. 7.
    Kruppa, H., Schiele, B.: Using local context to improve face detection. In: Proc. of the BMVC, Norwich, England, pp. 3–12 (2003) Google Scholar
  8. 8.
    Li, S., Zhu, L., Zhang, Z., Blake, A., Zhang, H., Shum, H.: Statistical learning of multi-view face detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 67–81. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  9. 9.
    Lindeberg, T.: Detecting salient blob-like image structures and their scales with a scale-space primal sketch - a method for focus-of-attention. International Journal of Computer Vision 11(3), 283–318 (1993)CrossRefGoogle Scholar
  10. 10.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. of the ICCV, Kerkyra, Greece, pp. 1150–1157 (1999)Google Scholar
  11. 11.
    Mikolajczyk, K., Choudhury, R., Schmid, C.: Face detection in a video sequence - a temporal approach. In: Proc. of the CVPR, Hawaii, USA, pp. 96–101 (2001)Google Scholar
  12. 12.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proc. of the CVPR, Madison, USA, pp. 257–263 (2003)Google Scholar
  13. 13.
    Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. IEEE Transactions on PAMI 23(4), 349–361 (2001)Google Scholar
  14. 14.
    Papageorgiou, C., Poggio, T.: A trainable system for object detection. International Journal of Computer Vision 38(1), 15–33 (2000)zbMATHCrossRefGoogle Scholar
  15. 15.
    Shapire, Y.S.R.E.: Improving bossting algorithm using confidence-rated predictions. Machine Learning 37(3), 297–336 (1999)CrossRefGoogle Scholar
  16. 16.
    Ramanan, D., Forsyth, D.A.: Finding and tracking people from the bottom up. In: Proc. of the CVPR, Madison, USA, pp. 467–474 (2003)Google Scholar
  17. 17.
    Ronfard, R., Schmid, C., Triggs, B.: Learning to parse pictures of people. In: Proc. of the ECCV, Copenhagen, Denmark, pp. 700–714 (2002)Google Scholar
  18. 18.
    Schneiderman, H.: Learning statistical structure for object detection. In: Proc. of the CAIP, Groningen, Netherlands, pp. 434–441 (2003)Google Scholar
  19. 19.
    Schneiderman, H., Kanade, T.: A statistical method for 3D object detection applied to faces and cars. In: Proc. of the CVPR, Hilton Head Island, USA, pp. 746–751 (2000)Google Scholar
  20. 20.
    Sidenbladh, H., Black, M.: Learning image statistics for bayesian tracking. In: Proc. of the ICCV, Vancouver, Canada, pp. 709–716 (2001)Google Scholar
  21. 21.
    Sigal, L., Isard, M., Sigelman, B.H., Black, M.J.: Attractive people: Assembling loose-limbed models using non-parametric belief propagation. In: Proc. of the NIPS, Vancouver, Canada (2003)Google Scholar
  22. 22.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. of the CVPR, Hawaii, USA, pp. 511–518 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  1. 1.Dept. of Engineering ScienceOxfordUnited Kingdom
  2. 2.INRIA Rhône-AlpesMontbonnotFrance

Personalised recommendations