Sequential Updating of Projective and Affine Structure from Motion
International Journal of Computer Vision
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Matching Widely Separated Views Based on Affine Invariant Regions
International Journal of Computer Vision
Wide Baseline Matching Through Homographic Transformation
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Wide-Baseline Stereo Matching with Line Segments
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Modeling of Environments: From Sparse Views to Obstacle Reconstruction
Modeling of Environments: From Sparse Views to Obstacle Reconstruction
| Hi-index | 0.00 |
This paper presents an approach to derive the equations of planar patches given a stereo pair of wide baseline or sparse view images. The algorithm starts by detecting junctions in both images using the so-called JUDOCA operator. A transformation matrix can be estimated using the junction attributes. In addition, a rough estimate for the fundamental matrix can be obtained to guide a matching process between the two views. Triangulation is used to reconstruct the locations of 2-edge junctions in space as well as to obtain the equations of 3D lines forming the junctions. This is done by obtaining four planes going through the projections of the junction edges and the optical centers. The equations of the 3D lines are used to get the equation of the plane of the junction.