Share Email Print

Proceedings Paper

Road. Following By An Autonomous Vehicle Using Range Data
Author(s): Uma Kant Sharma; Larry S. Davis
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper describes a road following system for an Autonomous Land Vehicle. Range data is used as the sensor input. The system is divided into two parts: low-level data driven analysis followed by high-level model-directed search. The sequence of steps performed, in order to detect 3-D road boundaries, is as follows: Range data is first converted from spherical into Cartesian coordinates. A quadric (or planar) surface is then fitted to the neighborhood of each range pixel, using a least square fit method. Based on this fit, minimum and maximum principal surface curvatures are computed at each point to detect edges. Next, using Hough transform techniques 3-D local line segments are extracted. Finally, model directed reasoning is applied to detect the road boundaries.

Paper Details

Date Published: 25 February 1987
PDF: 11 pages
Proc. SPIE 0727, Mobile Robots I, (25 February 1987); doi: 10.1117/12.937796
Show Author Affiliations
Uma Kant Sharma, FMC Corporation (United States)
Larry S. Davis, University of Maryland (United States)

Published in SPIE Proceedings Vol. 0727:
Mobile Robots I
Nelson Marquina; William J. Wolfe, Editor(s)

© SPIE. Terms of Use
Back to Top