This paper proposes a unified framework for spatiotemporal segmentation of video sequences. A Bayesian network is presented to model the interactions among the motion vector field, the intensity segmentation field, and the video segmentation field. The notions of distance transformation and Markov random field are used to express spatiotemporal constraints. Given consecutive frames, an optimization method is proposed to maximize the conditional probability density of the three fields in an iterative way. Experimental results show that the approach is robust and generates spatiotemporally coherent segmentation results.
Video segmentation based on graphical models
2003-01-01
933122 byte
Conference paper
Electronic Resource
English
Video Segmentation Based on Graphical Models
British Library Conference Proceedings | 2003
|Mixture of Trees Probabilistic Graphical Model for Video Segmentation
British Library Online Contents | 2014
|Optimising dynamic graphical models for video content analysis
British Library Online Contents | 2008
|British Library Online Contents | 2014
|Diagnostic assistant based on graphical probabilistic models
Automotive engineering | 2004
|