Publicação
Robust reconstruction of 3D points from images
| Resumo: | This paper presents a robust approach for 3D point recon- struction based on a set of images taken from a static scene with known, but not necessarily exact or regular, camera parameters. The points to be reconstructed are chosen from the contours of images, and a world-based formulationof the reconstruction problem and associated epipolar geom- etry is used. The result is a powerful mean of transpar- ently integrating contributions from multiple images, and increased robustness to situations such as occlusions or ap- parent contours. Two steps for adding robustness are pro- posed:cross-checking, which validates a reconstructed point taken from an image by projecting it on a special subset of the remaining images; andmerging, which fuses pairs of re- constructed points that are close in 3D space and that were initially chosen from different images. Results obtained with a synthetic scene (for ground truth comparison and error assessment), and two real scenes show the improved robustness achieved with the steps proposed. |
|---|---|
| Autores principais: | Rodrigues, Rui |
| Outros Autores: | Fernandes, António Ramires |
| Assunto: | 3d reconstruction Computer graphics |
| Ano: | 2004 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade do Minho |
| Idioma: | inglês |
| Origem: | RepositóriUM - Universidade do Minho |
| Resumo: | This paper presents a robust approach for 3D point recon- struction based on a set of images taken from a static scene with known, but not necessarily exact or regular, camera parameters. The points to be reconstructed are chosen from the contours of images, and a world-based formulationof the reconstruction problem and associated epipolar geom- etry is used. The result is a powerful mean of transpar- ently integrating contributions from multiple images, and increased robustness to situations such as occlusions or ap- parent contours. Two steps for adding robustness are pro- posed:cross-checking, which validates a reconstructed point taken from an image by projecting it on a special subset of the remaining images; andmerging, which fuses pairs of re- constructed points that are close in 3D space and that were initially chosen from different images. Results obtained with a synthetic scene (for ground truth comparison and error assessment), and two real scenes show the improved robustness achieved with the steps proposed. |
|---|