Maintaining multiple motion model hypotheses over many views to recover matching and structure
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 485-491
- https://doi.org/10.1109/iccv.1998.710762
Abstract
In order to recover structure from images it is desirable to use many views to obtain the best possible estimates. However, whilst recovering projective structure and motion from such extended sequences problems arise that are not apparent from a general view-point/structure approach. Foremost amongst these are (a) maintaining image correspondences consistently through many images, and (b) identifying images, within the sequence, for which structure cannot be reliably recovery. Within this paper the use of multiple motion model hypotheses is explored as an aid to solve both of these problems.Keywords
This publication has 7 references indexed in Scilit:
- An assessment of information criteria for motion model selectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Geometric motion segmentation and model selectionPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998
- A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometryArtificial Intelligence, 1995
- Outlier detection and motion segmentationPublished by SPIE-Intl Soc Optical Eng ,1993
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992
- Estimation of relative camera positions for uncalibrated camerasPublished by Springer Nature ,1992
- A multi-frame approach to visual motion perceptionInternational Journal of Computer Vision, 1991