Abstract | ||
---|---|---|
This paper presents a novel two-phase stereo matching algorithm using the random walks framework. At first, a set of reliable matching pixels is extracted with prior matrices defined on the penalties of different disparity configurations and Laplacian matrices defined on the neighbourhood information of pixels. Following this, using the reliable set as seeds, the disparities of unreliable regions are determined by solving a Dirichlet problem. The variance of illumination across different images is taken into account when building the prior matrices and the Laplacian matrices, which improves the accuracy of the resulting disparity maps. Even though random walks have been. used in. other applications, our work is the first application of random walks in stereo Matching. The proposed algorithm demonstrates good performance using the Middlebury stereo datasets. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICPR.2008.4761512 | 19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6 |
Keywords | Field | DocType |
mathematical model,probability,random processes,random walk,approximation algorithms,boundary value problems,image segmentation,pixel | Approximation algorithm,Computer vision,Dirichlet problem,Pattern recognition,Random walk,Computer science,Matrix (mathematics),Stochastic process,Image segmentation,Artificial intelligence,Pixel,Laplace operator | Conference |
ISSN | Citations | PageRank |
1051-4651 | 11 | 0.77 |
References | Authors | |
7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rui Shen | 1 | 128 | 6.03 |
Irene Cheng | 2 | 283 | 35.18 |
Xiaobo Li | 3 | 53 | 6.44 |
Anup Basu | 4 | 749 | 97.26 |