Automatic Classification And 3D Modeling Of Lidar Data
A. Moussa, and N. El-Sheimy. Proceedings of the ISPRS Commission III symposium - PCV 2010, volume 38 of International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, page 155-159. Saint-Mandé, France, ISPRS, (September 2010)
Abstract
LIght Detection And Ranging (LIDAR) data has been recognized as a valuable data source for mapping and 3D modelling of the Earth surface. Classification of LIDAR data for the purpose of extracting ground, vegetation, and buildings is a preliminary step to build 3D models. This paper presents a classification approach of single return LIDAR data that uses area growing technique to extract patches based on neighbourhood height similarity. The extracted patches are classified according to its area into buildings, vegetation, and ground. The classification technique exhibits fast results as it avoids the iterations needed by many classification techniques while maintaining high accuracy level. The presented technique enables simple tuning of parameters because it is directly related to the data specifications. The boundaries of the extracted buildings are then traversed to detect the significant points that help to build the 3D model. The heights of the significant points are computed using the neighbour ground points. Detailed results are presented to show the effectiveness of the proposed approach.
%0 Conference Paper
%1 Moussa2010
%A Moussa, A.
%A El-Sheimy, N.
%B Proceedings of the ISPRS Commission III symposium - PCV 2010
%C Saint-Mandé, France
%D 2010
%E Paparoditis, N.
%E Pierrot-Deseilligny, M.
%E Mallet, Clement
%E Tournaire, Olivier
%K Building classification Laserscanning modelling
%N Part 3B
%P 155-159
%T Automatic Classification And 3D Modeling Of Lidar Data
%V 38
%X LIght Detection And Ranging (LIDAR) data has been recognized as a valuable data source for mapping and 3D modelling of the Earth surface. Classification of LIDAR data for the purpose of extracting ground, vegetation, and buildings is a preliminary step to build 3D models. This paper presents a classification approach of single return LIDAR data that uses area growing technique to extract patches based on neighbourhood height similarity. The extracted patches are classified according to its area into buildings, vegetation, and ground. The classification technique exhibits fast results as it avoids the iterations needed by many classification techniques while maintaining high accuracy level. The presented technique enables simple tuning of parameters because it is directly related to the data specifications. The boundaries of the extracted buildings are then traversed to detect the significant points that help to build the 3D model. The heights of the significant points are computed using the neighbour ground points. Detailed results are presented to show the effectiveness of the proposed approach.
@inproceedings{Moussa2010,
abstract = {LIght Detection And Ranging (LIDAR) data has been recognized as a valuable data source for mapping and 3D modelling of the Earth surface. Classification of LIDAR data for the purpose of extracting ground, vegetation, and buildings is a preliminary step to build 3D models. This paper presents a classification approach of single return LIDAR data that uses area growing technique to extract patches based on neighbourhood height similarity. The extracted patches are classified according to its area into buildings, vegetation, and ground. The classification technique exhibits fast results as it avoids the iterations needed by many classification techniques while maintaining high accuracy level. The presented technique enables simple tuning of parameters because it is directly related to the data specifications. The boundaries of the extracted buildings are then traversed to detect the significant points that help to build the 3D model. The heights of the significant points are computed using the neighbour ground points. Detailed results are presented to show the effectiveness of the proposed approach.},
added-at = {2010-12-09T16:35:41.000+0100},
address = {Saint-Mandé, France},
author = {Moussa, A. and El-Sheimy, N.},
biburl = {https://www.bibsonomy.org/bibtex/21f9508c62c1de9800987c683e28fae53/ipi_jn},
booktitle = {Proceedings of the ISPRS Commission III symposium - PCV 2010},
editor = {Paparoditis, N. and Pierrot-Deseilligny, M. and Mallet, Clement and Tournaire, Olivier},
file = {:E\:\\Literatursammlung\\Proceedings\\ISPRS Com III - PCV Paris 2010\\Moussa (2010) - Automatic Classification And 3D Modelling of Lidar Data.pdf:PDF},
interhash = {ce3a320defbe0a14ce3e8ccf8f7c1abd},
intrahash = {1f9508c62c1de9800987c683e28fae53},
keywords = {Building classification Laserscanning modelling},
month = {September},
number = {Part 3B},
organization = {ISPRS},
pages = {155-159},
series = {International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences},
timestamp = {2010-12-09T16:35:41.000+0100},
title = {Automatic Classification And 3D Modeling Of Lidar Data},
volume = 38,
year = 2010
}