Robust Photo-Topography by Fusing Shape-from-Shading and Stereo
Abstract
Methods for fusing two computer vision methods are discussed and several example algorithms are presented to illustrate the variational method of fusing algorithms. The example algorithms solve the photo-topography problem; that is, the algorithms seek to determine planet topography given two images taken from two different locations with two different lighting conditions. The algorithms each employ a single cost function that combines the computer vision methods of shape-from-shading and stereo in different ways. The algorithms are closely coupled and take into account all the constraints of the photo- topography problem. One such algorithm, the z-only algorithm, can accurately and robustly estimate the height of a surface from two given images. Results of running the algorithms on four synthetic test image sets of varying difficulty are presented.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1993
- Accession Number
- ADA270885
Entities
People
- Clay M. Thompson
Organizations
- Massachusetts Institute of Technology