Abstract | ||
---|---|---|
In recent years, several kinds of tree structures for dynamic programming have been proposed. All the former trees only include pixels of the image. While in this paper, a new type of tree, which includes all the edges in the image, is constructed. In addition, weighted dynamic programming is proposed in order to improve the conventional dynamic programming. The weighted dynamic programming here is used to optimize the energy function of the new tree structure. Experiments show that our algorithm produces quite smooth and reasonable disparity maps which are close to the state-of-art. Evaluation on the Middlebury dataset shows that our method rank top in all the dynamic programming based stereo matching algorithms, even better than the algorithms that apply segmentation. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICIG.2011.26 | ICIG |
Keywords | Field | DocType |
conventional dynamic programming,energy function,new type,former tree,image matching,stereo matching,tree data structures,four-connected tree,weighted dynamic programming,middlebury dataset,image edges,tree structure,new tree structure,stereo matching algorithms,dynamic programming,stereo image processing,stereo algorithm,method rank top,heuristic algorithm,stereo vision,edge detection,databases,image segmentation | Stereo matching,Computer science,Stereopsis,Image segmentation,Artificial intelligence,Tree structure,Computer vision,Dynamic programming,Pattern recognition,Segmentation,Tree (data structure),Algorithm,Pixel | Conference |
ISBN | Citations | PageRank |
978-0-7695-4541-7 | 1 | 0.35 |
References | Authors | |
9 | 5 |