Recovery of ego-motion using region alignment
- 1 March 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 19 (3) , 268-272
- https://doi.org/10.1109/34.584105
Abstract
A method for computing the 3D camera motion (the ego-motion) in a static scene is described, where initially a detected 2D motion between two frames is used to align corresponding image regions. We prove that such a 2D registration removes all effects of camera rotation, even for those image regions that remain misaligned. The resulting residual parallax displacement field between the two region-aligned images is an epipolar field centered at the FOE (Focus-of-Expansion). The 3D camera translation is recovered from the epipolar field. The 3D camera rotation is recovered from the computed 3D translation and the detected 2D motion. The decomposition of image motion into a 2D parametric motion and residual epipolar parallax displacements avoids many of the inherent ambiguities and instabilities associated with decomposing the image motion into its rotational and translational components, and hence makes the computation of ego-motion or 3D structure estimation more robust.Keywords
This publication has 19 references indexed in Scilit:
- Robust structure from motion using motion parallaxPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Direct recovery of shape from multiple views: a parallax based approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Direct multi-resolution estimation of ego-motion and structure from motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Simple method for computing 3D motion and depthPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Parallax geometry of pairs of points for 3D scene analysisPublished by Springer Nature ,1996
- Computing occluding and transparent motionsInternational Journal of Computer Vision, 1994
- The coupling of rotation and translation in motion estimation of planar surfacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- A three-frame algorithm for estimating two-component image motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Relative orientationInternational Journal of Computer Vision, 1990
- Direct methods for recovering motionInternational Journal of Computer Vision, 1988