Name
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1109/CVPR.2003.1211488 | CVPR (2) |
Keywords | Field | DocType |
optimisation,motion vector,distance transformation,belief networks,graphical models,object-based video compression,conditional probability density maximization,image segmentation,spatiotemporal constraint,consecutive frame,optimization,video coding,image sequences,intensity segmentation,iterative maximization,video segmentation,multiple-object tracking,markov random field,markov processes,bayesian network,spatiotemporally coherent segmentation,spatiotemporal segmentation,probability,video sequence,image motion analysis,motion estimation,merging,distance transform,layout,video compression,robustness,graphical model,bayesian methods,conditional probability | Computer vision,Scale-space segmentation,Markov process,Pattern recognition,Segmentation,Markov random field,Computer science,Segmentation-based object categorization,Image segmentation,Bayesian network,Artificial intelligence,Graphical model | Conference |
Volume | ISSN | ISBN |
2 | 1063-6919 | 0-7695-1900-8 |
Citations | PageRank | References |
7 | 0.59 | 18 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yang Wang | 1 | 948 | 155.42 |
| Tele Tan | 2 | 173 | 28.33 |
| Kia-Fock Loe | 3 | 180 | 20.88 |