Learning Go/NoGo Terrain Classification
Abstract
This paper presents a software system for image-based terrain classification that mimics a human supervisor's segmentation and classification of training images into "Go" and "NoGo" regions. The system identifies a set of image chips in the training images that span the range of terrain appearance. It then uses these exemplars to segment novel images and assign fuzzy Go/NoGo classification. System parameters adapt to new inputs, providing a mechanism for learning.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 15, 2006
- Accession Number
- ADA578460
Entities
People
- Robert Karlsen
Organizations
- United States Army Tank Automotive Research, Development and Engineering Center