MLESAC: a new robust estimator with application to estimating image geometry
Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
Bayesian Model Estimation and Selection for Epipolar Geometry and Generic Manifold Fitting
International Journal of Computer Vision
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Robust Regression with Projection Based M-estimators
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
The Mars Exploration Rovers Descent Image Motion Estimation System
IEEE Intelligent Systems
MER-DIMES: A Planetary Landing Application of Computer Vision
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
RANSAC for (Quasi-)Degenerate data (QDEGSAC)
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
A vision-based navigation facility for planetary entry descent landing
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
Hi-index | 0.00 |
The paper is about the estimation of the relative position of a spacecraft, during the Entry Descent Landing (EDL) phase, by means of computer vision. A camera installed on board of the vehicle acquires images that are used for estimating the relative position of the camera between two consecutive images. A crucial point of the analysis, and the main objective of this work, is the estimation of the fundamental matrix F, considering the fact that in most cases we deal with a quasi-degenerate configuration. Indeed, the distance between the spacecraft (and the camera) and the planet surface, together with the morphology of the ground, make the problem difficult since most of the points will be extracted from a dominating plane. We discuss two different ways of addressing such degeneracy, while keeping the computational cost low, and present very promising results on synthetic as well as real image sequences.