Share Email Print
cover

Proceedings Paper

Classification and identification of small objects in complex urban-forested LIDAR data using machine learning
Author(s): William F. Basener; Abigail Basener
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Classification in LIDAR data is the process of determining points on terrain types and objects, often with the goal of determining land use and/or building footprints. In this paper we endeavor to classify terrain types and objects at a high level of detail in a complex scene that includes buildings, forested areas, and steep hillsides. Our object classes include buildings, building rooftop structures, forest trees, landscape trees, landscape bushes, cars, light posts of varying sizes, fences, paved surfaces, and grass. Our classification method of choice is a Random Forest, but we also investigate other machine learning methods including K-Nearest Neightbors and Linear Discriminant Analysis. We evaluate the effectiveness of the algorithms for accuracy, required training sample size, and runtime.

Paper Details

Date Published: 5 May 2017
PDF: 14 pages
Proc. SPIE 10191, Laser Radar Technology and Applications XXII, 101910F (5 May 2017); doi: 10.1117/12.2264641
Show Author Affiliations
William F. Basener, Univ. of Virginia (United States)
Rochester Institute of Technology (United States)
Abigail Basener, Tall Oaks Academy (United States)


Published in SPIE Proceedings Vol. 10191:
Laser Radar Technology and Applications XXII
Monte D. Turner; Gary W. Kamerman, Editor(s)

© SPIE. Terms of Use
Back to Top