Share Email Print
cover

Journal of Applied Remote Sensing

Automatic extraction of building boundaries using aerial LiDAR data
Author(s): Ruisheng Wang; Yong Hu; Huayi Wu; Jian Wang
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Building extraction is one of the main research topics of the photogrammetry community. This paper presents automatic algorithms for building boundary extractions from aerial LiDAR data. First, segmenting height information generated from LiDAR data, the outer boundaries of aboveground objects are expressed as closed chains of oriented edge pixels. Then, building boundaries are distinguished from nonbuilding ones by evaluating their shapes. The candidate building boundaries are reconstructed as rectangles or regular polygons by applying new algorithms, following the hypothesis verification paradigm. These algorithms include constrained searching in Hough space, enhanced Hough transformation, and the sequential linking technique. The experimental results show that the proposed algorithms successfully extract building boundaries at rates of 97%, 85%, and 92% for three LiDAR datasets with varying scene complexities.

Paper Details

Date Published: 8 March 2016
PDF: 20 pages
J. Appl. Remote Sens. 10(1) 016022 doi: 10.1117/1.JRS.10.016022
Published in: Journal of Applied Remote Sensing Volume 10, Issue 1
Show Author Affiliations
Ruisheng Wang, Univ. of Calgary (Canada)
Yong Hu, PCI Geomatics (Canada)
Huayi Wu, Wuhan Univ. (China)
Jian Wang, Shandong Univ. of Science and Technology (China)


© SPIE. Terms of Use
Back to Top