Segmentation and Tracking of Multiple Humans in Crowded Environments
Top Cited Papers
- 6 June 2008
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 30 (7) , 1198-1211
- https://doi.org/10.1109/tpami.2007.70770
Abstract
Segmentation and tracking of multiple humans in crowded situations is made difficult by interobject occlusion. We propose a model-based approach to interpret the image observations by multiple partially occluded human hypotheses in a Bayesian framework. We define a joint image likelihood for multiple humans based on the appearance of the humans, the visibility of the body obtained by occlusion reasoning, and foreground/background separation. The optimal solution is obtained by using an efficient sampling method, data-driven Markov chain Monte Carlo (DDMCMC), which uses image observations for proposal probabilities. Knowledge of various aspects, including human shape, camera model, and image cues, are integrated in one theoretically sound framework. We present experimental results and quantitative evaluation, demonstrating that the resulting approach is effective for very challenging data.Keywords
This publication has 41 references indexed in Scilit:
- Real-Time Wide Area Multi-Camera Stereo TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Strike a Pose: Tracking People by Finding Stylized PosesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A model-based vehicle segmentation method for trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Bayesian human segmentation in crowded situationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Detecting moving shadows: algorithms and evaluationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Image segmentation by data-driven markov chain monte carloPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Object tracking with Bayesian estimation of dynamic layer representationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learning patterns of activity using real-time trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Correctness of Local Probability Propagation in Graphical Models with LoopsNeural Computation, 2000