A Methodology for Extraction Building Facades from VLS

Author

Zuo-Wei Huang ; Xiang Chi ; Fang Liu

Author_Institution

Hunan Univ. of Technol., Zhuzhou, China

fYear

2012

fDate

July 31 2012-Aug. 2 2012

Firstpage

77

Lastpage

80

Abstract

The components and position principle of vehicle-borne LIDAR system are expatiated. Based on the previous experience a new method for automated extraction of building facades from VLS was put forward. It adopt image segmentation and contour extraction tracing to extract building boundaries in the geo-referenced feature image. the existing methods of RANSAC, point cloud segmentation, feature extraction are analyzed, At last the experimental results show that the proposed method provides useful and valid solution for automatically extracting building footprints from mobile LIDAR point clouds.

Keywords

feature extraction; image segmentation; optical radar; radar imaging; RANSAC; VLS; automatically extracting building footprints; building boundaries; building facades automated extraction; building facades extraction; contour extraction; feature extraction; geo-referenced feature image; image segmentation; mobile LIDAR point clouds; point cloud segmentation; vehicle-borne LIDAR system; Buildings; Data models; Feature extraction; Image segmentation; Laser radar; Lasers; Mobile communication; Feature Extraction; Point Cloud Segmentation; VLS;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Manufacturing and Automation (ICDMA), 2012 Third International Conference on

Conference_Location

GuiLin

Print_ISBN

978-1-4673-2217-1

Type

conf

DOI

10.1109/ICDMA.2012.18

Filename

6298258