Methods for ground target detection and recognition in 3-D laser data

Authors:

  • Chevalier Tomas
  • Tolt Gustav
  • Andersson Pierre
  • Grönwall Christina

Publish date: 2006-01-01

Report number: FOI-R--2150--SE

Pages: 37

Written in: English

Abstract

The signal processing of three-dimensional laser data is a relatively new field of research, especially the high resolution applications. The laser based 3-D sensors give contrast where passive 2-D sensors in general have small or no contrast, as for instance in darkness. They give the possibility to separate objects at different distances. As long as you have some light passing through a covering material, such as for most cloth, vegetation, smoke, and Venetian blinds, it is possible to get a geometric view of the hidden objects. This geometric object data can be used for absolute measurements and is therefore also a strong basis for recognition. This report shows some of the studied methods to detect, segment and recognize objects in 3-D laser data and gives some examples. Only sensor systems placed on ground or close to ground in a fairly low angle of incidence are considered.