Machine interpretation of line drawings
Machine interpretation of line drawings
The Entry-Exit Method of Shadow Boundary Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shadow segmentation and classification in a constrained environment
CVGIP: Image Understanding
Constrained Structure and Motion From Multiple Uncalibrated Views of a Piecewise Planar Scene
International Journal of Computer Vision
On 3-D Surface Reconstruction Using Shape from Shadows
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Cast shadow segmentation using invariant color features
Computer Vision and Image Understanding
Vertical Parallax from Moving Shadows
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
3D Reconstruction by Shadow Carving: Theory and Practical Evaluation
International Journal of Computer Vision
Dense 3D Reconstruction method using Coplanarities and Metric Constraints for Line Laser Scanning
3DIM '07 Proceedings of the Sixth International Conference on 3-D Digital Imaging and Modeling
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
| Hi-index | 0.00 |
To date, various techniques of shape reconstruction using cast shadows have been proposed. The techniques have the advantage that they can be applied to various scenes including outdoor scenes without using special devices. Previously proposed techniques usually require calibration of camera parameters and light source positions, and such calibration processes make the application ranges limited. If a shape can be reconstructed even when these values are unknown, the technique can be used to wider range of applications. In this paper, we propose a method to realize such a technique by constructing simultaneous equations from coplanarities and metric constraints, which are observed by cast shadows of straight edges and visible planes in the scenes, and solving them. We conducted experiments using simulated and real images to verify the technique.