Abstract | ||
---|---|---|
This paper presents an algorithm that augments a previous model known in the literature for the automatic segmentation of monocular videos into foreground and background layers. The original model fuses visual cues such as color, contrast, motion and spatial priors within a Conditional Random Field. Our augmented model makes use of bidirectional motion priors by exploiting future evidence. Although our augmented model processes more data, it does so with the same time performance of the original model. We evaluate the augmented model within ground truth data and the results show that the augmented model produces better segmentation. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-31075-1_52 | ICCSA |
Keywords | Field | DocType |
bidirectional motion prior,future evidence,previous model,ground truth data,original model,automatic segmentation,background layer,better segmentation,bilayer segmentation,conditional random field,augmented model,computer vision | Conditional random field,Sensory cue,Computer vision,Scale-space segmentation,Computer science,Segmentation,Ground truth,Artificial intelligence,Fuse (electrical),Monocular,Prior probability | Conference |
Volume | ISSN | Citations |
7334 | 0302-9743 | 1 |
PageRank | References | Authors |
0.36 | 17 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Silvio Ricardo Rodrigues Sanches | 1 | 20 | 4.03 |
Valdinei Freire da Silva | 2 | 25 | 6.86 |
Romero Tori | 3 | 63 | 16.24 |