Fast Stereo Matching Using Rectangular Subregioning and 3D Maximum-Surface Techniques
International Journal of Computer Vision
Bundle Adjustment - A Modern Synthesis
ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Speeded-Up Robust Features (SURF)
Computer Vision and Image Understanding
Photometric Recovery of Ortho-Images Derived from Apollo 15 Metric Camera Imagery
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
3D Lunar Terrain Reconstruction from Apollo Images
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
A Bayesian formulation for sub-pixel refinement in stereo orbital imagery
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Probabilistic matching of lines for their homography
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
| Hi-index | 0.00 |
Robust estimation method is proposed to combine multiple observations and create consistent, accurate, dense Digital Elevation Models (DEMs) from lunar orbital imagery. The NASA Ames Intelligent Robotics Group (IRG) aims to produce higher-quality terrain reconstructions of the Moon from Apollo Metric Camera (AMC) data than is currently possible. In particular, IRG makes use of a stereo vision process, the Ames Stereo Pipeline (ASP), to automatically generate DEMs from consecutive AMC image pairs. However, the DEMs currently produced by the ASP often contain errors and inconsistencies due to image noise, shadows, etc. The proposed method addresses this problem by making use of multiple observations and by considering their goodness of fit to improve both the accuracy and robustness of the estimate. The stepwise regression method is applied to estimate the relaxed weight of each observation.