Share Email Print

Proceedings Paper

Application of image classification techniques to multispectral lidar point cloud data
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Data from Optech Titan are analyzed here for purposes of terrain classification, adding the spectral data component to the lidar point cloud analysis. Nearest-neighbor sorting techniques are used to create the merged point cloud from the three channels. The merged point cloud is analyzed using spectral analysis techniques that allow for the exploitation of color, derived spectral products (pseudo-NDVI), as well as lidar features such as height values, and return number. Standard spectral image classification techniques are used to train a classifier, and analysis was done with a Maximum Likelihood supervised classification. Terrain classification results show an overall accuracy improvement of 10% and a kappa coefficient increase of 0.07 over a raster-based approach.

Paper Details

Date Published: 13 May 2016
PDF: 12 pages
Proc. SPIE 9832, Laser Radar Technology and Applications XXI, 98320X (13 May 2016); doi: 10.1117/12.2223257
Show Author Affiliations
Chad I. Miller, Science Applications International Corp. (United States)
Naval Postgraduate School (United States)
Judson J. Thomas, Naval Postgraduate School (United States)
Angela M. Kim, Naval Postgraduate School (United States)
Jeremy P. Metcalf, Naval Postgraduate School (United States)
Richard C. Olsen, Naval Postgraduate School (United States)

Published in SPIE Proceedings Vol. 9832:
Laser Radar Technology and Applications XXI
Monte D. Turner; Gary W. Kamerman, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?