| Summary: | The objective of this work is to automatically estimate the trifocal tensor and feature correspondences over images triplets, under unrestricted camera motions and changes in internal parameters between views. To this end we extend a previous wide baseline 2-view algorithm to 3-views. The algorithm is based on establishing feature correspondences between views together with a homography which enables a viewpoint invariant affinity score. The input is the three images, and the output the trifocal tensor and image correspondences, which in turn facilitate a projective reconstruction of the cameras and scene.
<br>
We also investigate the direct computation of the fundamental matrix for view pairs, and the trifocal tensor for view triplets, from the homographies alone. This method is successful, but not as yet as accurate as computation from point correspondences.
<br>
Finally, it is shown that the 3-view algorithm allows reconstruction of 3D points, lines and cameras from a disparate set of 11 views. All the algorithms have been implemented and assessed on real images, and processing is automatic throughout.
|
|---|