The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XL-5
https://doi.org/10.5194/isprsarchives-XL-5-77-2014
https://doi.org/10.5194/isprsarchives-XL-5-77-2014
05 Jun 2014
 | 05 Jun 2014

Automatic Classification of coarse density LiDAR data in urban area

H.M. Badawy, A. Moussa, and N. El-Sheimy

Keywords: LIDAR, Vehicle, Classification, Airborne, Urban, PCA, NDSM, DTM

Abstract. The classification of different objects in the urban area using airborne LIDAR point clouds is a challenging problem especially with low density data. This problem is even more complicated if RGB information is not available with the point clouds. The aim of this paper is to present a framework for the classification of the low density LIDAR data in urban area with the objective to identify buildings, vehicles, trees and roads, without the use of RGB information. The approach is based on several steps, from the extraction of above the ground objects, classification using PCA, computing the NDSM and intensity analysis, for which a correction strategy was developed. The airborne LIDAR data used to test the research framework are of low density (1.41 pts/m2) and were taken over an urban area in San Diego, California, USA. The results showed that the proposed framework is efficient and robust for the classification of objects.