Advertisement

Crowd Segmentation Through Emergent Labeling

  • Peter H. Tu
  • Jens Rittscher
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3247)

Abstract

As an alternative to crowd segmentation using model-based object detection methods which depend on learned appearance models, we propose a paradigm that only makes use of low-level interest points. Here the detection of objects of interest is formulated as a clustering problem. The set of feature points are associated with vertices of a graph. Edges connect vertices based on the plausibility that the two vertices could have been generated from the same object. The task of object detection amounts to identifying a specific set of cliques of this graph. Since the topology of the graph is constrained by a geometric appearance model the maximal cliques can be enumerated directly. Each vertex of the graph can be a member of multiple maximal cliques. We need to find an assignment such that every vertex is only assigned to a single clique. An optimal assignment with respect to a global score function is estimated though a technique akin to soft-assign which can be viewed as a form of relaxation labeling that propagates constraints from regions of low to high ambiguity. No prior knowledge regarding the number of people in the scene is required.

Keywords

Interest Point Maximal Clique Acceptance Probability Edge Strength Blob Detection 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Elgammal, A., Duraiswami, R., Harwood, D., Davis, L.: Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE 90(7), 1151–1163 (2002)CrossRefGoogle Scholar
  2. 2.
    Gavrila, D.: Pedestrian detection from a moving vehicle. In: Proc. 6th European Conf., Computer Vision, Dublin, Ireland, pp. 37–49 (2000)Google Scholar
  3. 3.
    Gold, S., Rangarajan, A.: A graduated assignment algorithm for graph matching. IEEE Trans. on Pattern Analysis and Machine Intelligence 18(4), 377–388 (1996)CrossRefGoogle Scholar
  4. 4.
    Hartley, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  5. 5.
    Intille, S.S., Davis, J.W., Bobick, A.F.: Real time closed world tracking. In: Proc. 11th IEEE Computer Vision and Pattern Recognition, San Jaun, PR, pp. 697–703 (1997)Google Scholar
  6. 6.
    Pelillo, M., Pavan, M.: A new graph-theoretric approach to clustering and segmentation. In: IEEE Computer Vision and Pattern Recognition, Madison, Wisconsin, pp. 145–152 (2003)Google Scholar
  7. 7.
    Zucker, S., Pelillo, M., Siddiqi, K.: Matching hierarchical structures using association graphs. IEEE Trans. on Pattern Analysis and Machine Intelligence 21(11), 1105–1119 (1999)CrossRefGoogle Scholar
  8. 8.
    Mittal, A., Davis, L.S.: M2tracker: A multi-view approach to segmenting and tracking people in a cluttered scene using region-based stereo. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 18–33. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  9. 9.
    Nakajima, C., Pontil, M., Heisele, B., Poggio, T.: People recognition in image sequences by supervised learning. In: MIT AI Memo (2000)Google Scholar
  10. 10.
    Ronfard, R., Schmid, C., Triggs, B.: Learning to parse pictures of people. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 700–714. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  11. 11.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(8), 888–905 (2000)CrossRefGoogle Scholar
  12. 12.
    Zhao, T., Nevatia, R.: Stochastic human segmentation from a static camera. In: IEEE Workshop on Motion and Video Computing, Orlando, FL, USA, pp. 9–14 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Peter H. Tu
    • 1
  • Jens Rittscher
    • 1
  1. 1.GE Global Research, One Research CircleNiskayunaUSA

Personalised recommendations