Vision for mobile robots
- 29 September 1992
- journal article
- Published by The Royal Society in Philosophical Transactions Of The Royal Society B-Biological Sciences
- Vol. 337 (1281) , 341-350
- https://doi.org/10.1098/rstb.1992.0112
Abstract
Localized feature points, particularly corners, can be computed rapidly and reliably in images, and they are stable over image sequences. Corner points provide more constraint than edge points, and this additional constraint can be propagated effectively from corners along edges. Implemented algorithms are described to compute optic flow and to determine scene structure for a mobile robot using stereo or structure from motion. It is argued that a mobile robot may not need to compute depth explicitly in order to navigate effectively.Keywords
This publication has 14 references indexed in Scilit:
- Model-based recognition and range imaging for a guided vehicleImage and Vision Computing, 1992
- Parallel computation of optic flowPublished by Springer Nature ,1990
- Robust estimation of surface curvature from deformation of apparent contoursPublished by Springer Nature ,1990
- On the estimation of optical flow: Relations between different approaches and some new resultsArtificial Intelligence, 1987
- Surface representations based on triangular gridsThe Visual Computer, 1987
- Using Canny's criteria to derive a recursively implemented optimal edge detectorInternational Journal of Computer Vision, 1987
- A Computational Approach to Edge DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- The Curvature Primal SketchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- PMF: A Stereo Correspondence Algorithm Using a Disparity Gradient LimitPerception, 1985
- A Disparity Gradient Limit for Binocular FusionScience, 1980