Abstract | ||
---|---|---|
Stereo image segmentation usually incorporates depth cues to achieve high quality. However, previous methods that pointwise propagate information within stereo pairs could suffer from a poorly estimated depth map. In this paper, we introduce a novel graphical model where a greater amount of reliable messages can be conveyed during two-view joint segmentation. This model leads to a strongly coupled stereo pair, thus improving robustness, accuracy and consistency of stereo segmentation. Additionally, we augment a depth map to a novel correspondence matrix which is suitable for the proposed stereo segmentation model. Our experiments on a public stereo dataset show that the proposed correspondence method and stereo model outperforms state-of-the-art stereo segmentation algorithms. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICME.2013.6607457 | ICME |
Keywords | Field | DocType |
depth map,bi-layer segmentation,random processes,bilayer image segmentation,correspondence matrix,public stereo dataset,image segmentation,matrix algebra,two-view joint segmentation,graphical model,stereo random field,random field,stereo,stereo image segmentation,depth cues,stereo image processing,accuracy,robustness | Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Robustness (computer science),Image segmentation,Artificial intelligence,Graphical model,Depth map,Pointwise,Computer stereo vision | Conference |
ISSN | Citations | PageRank |
1945-7871 | 0 | 0.34 |
References | Authors | |
11 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kuo-Chin Lien | 1 | 95 | 6.46 |
Jerry D. Gibson | 2 | 338 | 48.12 |