Ego-motion and omnidirectional cameras
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 999-1005
- https://doi.org/10.1109/iccv.1998.710838
Abstract
Recent research in image sensors has produced cameras with very large fields of view. An area of computer vision research which will benefit from this technology is the computation of camera motion (ego-motion) from a sequence of images. Traditional cameras stiffer from the problem that the direction of translation may lie outside of the field of view, making the computation of camera motion sensitive to noise. In this paper, we present a method for the recovery of ego-motion using omnidirectional cameras. Noting the relationship between spherical projection and wide-angle imaging devices, we propose mapping the image velocity vectors to a sphere, using the Jacobian of the transformation between the projection model of the camera and spherical projection. Once the velocity vectors are mapped to a sphere, we show how existing ego-motion algorithms can be applied and present some experimental results. These results demonstrate the ability to compute ego-motion with omnidirectional cameras.Keywords
This publication has 17 references indexed in Scilit:
- Probability distributions of optical flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A fast subspace algorithm for recovering rigid motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Catadioptric omnidirectional cameraPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Real-time obstacle avoidance using central flow divergence and peripheral flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Panoramic image acquisitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Comparison of approaches to egomotion computationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Direct Perception of Three-Dimensional Motion from Patterns of Visual MotionScience, 1995
- Plenoptic modelingPublished by Association for Computing Machinery (ACM) ,1995
- Finding motion parameters from spherical motion fields (or the advantages of having eyes in the back of your head)Biological Cybernetics, 1988
- Passive navigationComputer Vision, Graphics, and Image Processing, 1983