Abstract | ||
---|---|---|
3D reconstruction from multiple view images requires that camera parameters are very accurately known and standard camera calibration techniques [1] often fail to provide the required level of accuracy for the extrinsic camera parameters. Using the Kinect depth camera, we propose to estimate camera parameters by minimising the cross correlation between density functions modelled for each recorded depth images. We illustrate experimentally how this improves the modelling for estimating 3D shape from Depths. |
Year | Venue | Keywords |
---|---|---|
2012 | European Signal Processing Conference | Shape-from-Silhouettes (SfS),Shape-from-Depths (SfD),Multiview geometry |
Field | DocType | ISSN |
Cross-correlation,Iterative reconstruction,Computer vision,Computer graphics (images),Camera auto-calibration,Camera resectioning,Artificial intelligence,Estimation theory,Mathematics,Calibration,3D reconstruction | Conference | 2076-1465 |
Citations | PageRank | References |
2 | 0.36 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jonathan Ruttle | 1 | 12 | 2.75 |
Claudia Arellano | 2 | 9 | 1.82 |
Rozenn Dahyot | 3 | 340 | 32.62 |