Crowd Segmentation Through Emergent Labeling
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.
KeywordsInterest Point Maximal Clique Acceptance Probability Edge Strength Blob Detection
Unable to display preview. Download preview PDF.
- 2.Gavrila, D.: Pedestrian detection from a moving vehicle. In: Proc. 6th European Conf., Computer Vision, Dublin, Ireland, pp. 37–49 (2000)Google Scholar
- 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.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
- 9.Nakajima, C., Pontil, M., Heisele, B., Poggio, T.: People recognition in image sequences by supervised learning. In: MIT AI Memo (2000)Google Scholar
- 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