The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XXXVIII-5/W12
https://doi.org/10.5194/isprsarchives-XXXVIII-5-W12-13-2011
https://doi.org/10.5194/isprsarchives-XXXVIII-5-W12-13-2011
03 Sep 2012
 | 03 Sep 2012

HEURISTICAL FEATURE EXTRACTION FROM LIDAR DATA AND THEIR VISUALIZATION

S. Ghosh and B. Lohani

Keywords: LIDAR, segmentation, feature extraction, visualization

Abstract. Extraction of landscape features from LiDAR data has been studied widely in the past few years. These feature extraction methodologies have been focussed on certain types of features only, namely the bare earth model, buildings principally containing planar roofs, trees and roads. In this paper, we present a methodology to process LiDAR data through DBSCAN, a density based clustering method, which extracts natural and man-made clusters. We then develop heuristics to process these clusters and simplify them to be sent to a visualization engine.