Finding and tracking people from the bottom up
- 20 November 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 467
- https://doi.org/10.1109/cvpr.2003.1211504
Abstract
We describe a tracker that can track moving people in long sequences without manual initialization. Moving peo- ple are modeled with the assumption that, while configura- tion can vary quite substantially from frame to frame, ap- pearance does not. This leads to an algorithm that firstly builds a model of the appearance of the body of each indi- vidual by clustering candidate body segments, and then uses this model to find all individuals in each frame. Unusually, the tracker does not rely on a model of human dynamics to identify possible instances of people; such models are un- reliable, because human motion is fast and large accelera- tions are common. We show our tracking algorithm can be interpreted as a loopy inference procedure on an underlying Bayes net. Experiments on video of real scenes demonstrate that this tracker can (a) count distinct individuals; (b) iden- tify and track them; (c) recover when it loses track, for ex- ample, if individuals are occluded or briefly leave the view; (d) identify the configuration of the body largely correctly; and (e) is not dependent on particular models of human mo- tion.Keywords
This publication has 10 references indexed in Scilit:
- Incremental recognition of pedestrians from image sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Tracking people with twists and exponential mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Human tracking with mixtures of treesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Efficient matching of pictorial structuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Articulated body motion capture by annealed particle filteringPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Towards detection of human motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Mean shift: a robust approach toward feature space analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learning Montages of Transformed Latent Images as Representations of Objects That Change in AppearancePublished by Springer Nature ,2002
- Probabilistic Tracking with Exemplars in a Metric SpaceInternational Journal of Computer Vision, 2002
- Model-based vision: a program to see a walking personImage and Vision Computing, 1983