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.

Open PDF

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

Tags

Communities of Interest

  • Air Platforms
  • Autonomy

DTIC Thesaurus Topics

  • Applied Computer Science
  • Artificial Intelligence Computing
  • Autonomous Navigation
  • Cameras
  • Classification
  • Clustering
  • Coding
  • Color Coding
  • Computational Science
  • Computer Vision
  • Coordinate Systems
  • Decoding
  • Learning
  • Robot Navigation
  • Robots
  • Training
  • Visualizations

Fields of Study

  • Computer science

Readers

  • Computer Vision.