Share Email Print

Proceedings Paper

Vision-based terrain learning
Author(s): Robert E. Karlsen; Gary Witus
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper presents an algorithm for online image-based terrain classification that mimics a human supervisor's segmentation and classification of training images into "Go" and "NoGo" regions. The algorithm identifies a set of image chips (or exemplars) in the training images that span the range of terrain appearance. It then uses the exemplars to segment novel images and assign a Go/NoGo classification. System parameters adapt to new inputs, providing a mechanism for learning. System performance is compared to that obtained via offline fuzzy c-means clustering and support vector machine classification.

Paper Details

Date Published: 9 May 2006
PDF: 10 pages
Proc. SPIE 6230, Unmanned Systems Technology VIII, 623005 (9 May 2006); doi: 10.1117/12.664427
Show Author Affiliations
Robert E. Karlsen, U.S. Army - TARDEC (United States)
Gary Witus, Turing Associates (United States)

Published in SPIE Proceedings Vol. 6230:
Unmanned Systems Technology VIII
Grant R. Gerhart; Charles M. Shoemaker; Douglas W. Gage, Editor(s)

© SPIE. Terms of Use
Back to Top