Title | ||
---|---|---|
Dependable dense stereo matching by both two-layer recurrent process and chaining search |
Abstract | ||
---|---|---|
Disparity computation in occluded or texture-less regions is considered to be a fundamental issue in dense stereo matching, but there is another practical issue that must be resolved before it can be used effectively in various robotics applications. This issue is the problem of intensity difference between corresponding pixels of an image pair. To tackle such problems, we present a dependable stereo matching algorithm using two-layer recurrent process and chaining search. Two-layer process integrates pixel and region-levels information through recurrent interaction. To estimate the precise disparities in occluded regions, reliable disparities in non-occluded region are propagated to occluded regions by the proposed chaining search. To test our algorithm, it was compared with two outstanding algorithms in Middlebury benchmark using Gaussian noisy images. The results validated the effectiveness of our approach. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/IROS.2012.6386179 | IROS |
Keywords | Field | DocType |
texture-less regions,image matching,occluded regions,robotics applications,gaussian noisy images,disparity computation,image pair pixel,gaussian processes,middlebury benchmark,dependable stereo matching algorithm,stereo image processing,two-layer recurrent process,image texture,pixel-level information,chaining search,region-level information,intensity difference,robot vision,image segmentation,psnr,robots,reliability,computational modeling,stereo vision | Template matching,Computer vision,Stereo cameras,Chaining,Image texture,Stereopsis,Computer science,Image segmentation,Artificial intelligence,Pixel,Computer stereo vision | Conference |
ISSN | ISBN | Citations |
2153-0858 | 978-1-4673-1737-5 | 0 |
PageRank | References | Authors |
0.34 | 12 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sehyung Lee | 1 | 0 | 0.34 |
Youngbin Park | 2 | 4 | 5.85 |
Il Hong Suh | 3 | 780 | 110.60 |