We describe an approach to recovering surface models of complex scenes from the quasisparse data returned by a feature based stereo system. The method can be used to merge stereo results obtained from different viewpoints into a single coherent surface mesh. The technique proceeds by exploiting the freespace theorem which provides a principled mechanism for reasoning about the structure of the scene based on quasisparse correspondences in multiple image. Effective methods for overcoming the difficulties posed by missing features and outliers are discussed. Results obtained by applying this approach to actual images are presented.
Surface reconstruction from feature based stereo
2003-01-01
1821589 byte
Conference paper
Electronic Resource
English
Surface Reconstruction from Feature Based Stereo
British Library Conference Proceedings | 2003
|Segmented-Region Based Stereo Reconstruction
SPIE | 1986
|British Library Conference Proceedings | 2002
|Distributed Wireless Stereo Reconstruction
British Library Conference Proceedings | 1997
|