Point cloud segmentation towards urban ground modeling

Author

Hernández, Jorge ; Marcotegui, Beatriz

Author_Institution

CMM- Centre de Morphologie Math., Mines ParisTech, Fontainebleau

fYear

2009

fDate

20-22 May 2009

Firstpage

1

Lastpage

5

Abstract

This paper presents a new method for segmentation and interpretation of 3D point clouds from mobile LIDAR data. The main contribution of this work is the automatic detection and classification of artifacts located at the ground level. The detection is based on Top-Hat of hole filling algorithm of range images. Then, several features are extracted from the detected connected components (CCs). Afterward, a stepwise forward variable selection by using Wilk´s Lambda criterion is performed. Finally, CCs are classified in four categories (lampposts, pedestrians, cars, the others) by using a SVM machine learning method.

Keywords

feature extraction; geophysical techniques; image segmentation; optical radar; remote sensing by radar; support vector machines; SVM machine learning method; Top-Hat; Wilk´s Lambda criterion; artifacts detection; automatic classification; automatic detection; connected components; feature extraction; hole filling algorithm; mobile LIDAR data; point cloud segmentation method; urban ground modeling; Carbon capture and storage; Clouds; Data mining; Feature extraction; Filling; Image segmentation; Input variables; Laser radar; Machine learning algorithms; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Urban Remote Sensing Event, 2009 Joint

Conference_Location

Shanghai

Print_ISBN

978-1-4244-3460-2

Electronic_ISBN

978-1-4244-3461-9

Type

conf

DOI

10.1109/URS.2009.5137562

Filename

5137562