This paper describes a framework for learning probabilistic models of objects and scenes and for exploiting these models for tracking complex, deformable, or articulated objects in image sequences. We focus on the probabilistic tracking of people and learn models of how they appear and move in images. In particular we learn the likelihood of observing various spatial and temporal filter responses corresponding to edges, ridges, and motion differences given a model of the person. Similarly, we learn probability distributions over filter responses for general scenes that define a likelihood of observing the filter responses for arbitrary backgrounds. We then derive a probabilistic model for tracking that exploits the ratio between the likelihood that image pixels corresponding to the foreground (person) were generated by an actual person or by some unknown background. The paper extends previous work on learning image statistics and combines it with Bayesian tracking using particle filtering. By combining multiple image cues, and by using learned likelihood models, we demonstrate improved robustness and accuracy when tracking complex objects such as people in monocular image sequences with cluttered scene and a moving camera.
Learning image statistics for Bayesian tracking
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 2 ; 709-716 vol.2
2001-01-01
1177694 byte
Conference paper
Electronic Resource
English
Learning Image Statistics for Bayesian Tracking
British Library Conference Proceedings | 2001
|Terrain navigation using Bayesian statistics
Tema Archive | 1999
|Bayesian statistics on engine mapping
Automotive engineering | 2002
|Multistatic Bayesian extended target tracking
IEEE | 2016
|