Fusing Laser Reflectance and Image Data for Terrain Classification for Small Autonomous Robots

Abstract

Knowing the terrain is vital for small autonomous robots traversing unstructured outdoor environments. We present a technique using 3D laser point clouds combined with RGB camera images to classify terrain into four pre-defined classes grass, sand, concrete, and metal. Our technique first segments the point cloud into distinct regions and then applies a simple classifier to determine the classification of each region. We demonstrate three classification and four segmentation algorithms on five outdoor environments. Classification and segmentation algorithms which use more information outperform information poor combinations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2014
Accession Number
ADA618994

Entities

People

  • Donald Sofge
  • Keith M. Sullivan
  • Wallace Lawson

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy
  • Ground and Sea Platforms
  • Sensors

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Autonomous Navigation
  • Classification
  • Computer Vision
  • Concrete
  • Environment
  • Information Surveillance
  • Materials
  • Military Research
  • Navigation
  • Point Clouds
  • Probability
  • Probability Distributions
  • Reflectance
  • Robot Navigation
  • Robots

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Robotics and Automation.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy
  • Directed Energy