Name
Abstract | ||
|---|---|---|
One of the key problems in computer vision is the recov- ery of epipolar geometry constraints between different camera views. The majority of existing techniques rely on point cor- respondences, which are typically perturbed by mismatches and noise, hence limiting the accuracy of these techniques. To overcome these limitations, we propose a novel approach that estimates epipolar geometry constraints based on a statis- tical model in the RADON domain. The method requires no correspondences, explicit constraints on the data or assump- tions regarding the scene structure. Results are presented on both synthetic and real data that show the method's robustness to noise and outliers. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/ICASSP.2006.1660388 | ICASSP (2) |
Keywords | Field | DocType |
cost function,image reconstruction,statistical analysis,information geometry,computer vision,fundamental matrix,radon transform,computational geometry,layout,statistical model,epipolar geometry,information technology | Iterative reconstruction,Information geometry,Computer vision,Mathematical optimization,Epipolar geometry,Computer science,Computational geometry,Robustness (computer science),Statistical model,Artificial intelligence,Radon transform,Fundamental matrix (computer vision) | Conference |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stefan Lehmann | 1 | 0 | 0.34 |
| Andrew P. Bradley | 2 | 2087 | 195.95 |
| I. Vaughan | 3 | 0 | 0.34 |
| L. Clarkson | 4 | 0 | 0.34 |