A robust correspondence matching algorithm of ground images along the optic axis
| Autor: | Zhizhong Kang, Fengman Jia |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
business.industry
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Principal point Scale-invariant feature transform Real image Optical axis Robustness (computer science) Computer Science::Computer Vision and Pattern Recognition Image pair Computer vision Artificial intelligence Affine transformation business Blossom algorithm Mathematics |
| Zdroj: | SPIE Proceedings. |
| ISSN: | 0277-786X |
| Popis: | Facing challenges of nontraditional geometry, multiple resolutions and the same features sensed from different angles, there are more difficulties of robust correspondence matching for ground images along the optic axis. A method combining SIFT algorithm and the geometric constraint of the ratio of coordinate differences between image point and image principal point is proposed in this paper. As it can provide robust matching across a substantial range of affine distortion addition of change in 3D viewpoint and noise, we use SIFT algorithm to tackle the problem of image distortion. By analyzing the nontraditional geometry of ground image along the optic axis, this paper derivates that for one correspondence pair, the ratio of distances between image point and image principal point in an image pair should be a value not far from 1. Therefore, a geometric constraint for gross points detection is formed. The proposed approach is tested with real image data acquired by Kodak. The results show that with SIFT and the proposed geometric constraint, the robustness of correspondence matching on the ground images along the optic axis can be effectively improved, and thus prove the validity of the proposed algorithm. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|