Fusion of LIDAR data and large-scale vector maps for building reconstruction

Liang Chien Chen, Chih Yi Kuo, Jiann-Yeou Rau, Chi Heng Hsieh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

LIDAR data contains plenty of height information, while vector maps preserve accurate building boundaries. From the viewpoint of data fusion, we integrate LIDAR data and large-scale vector maps to perform building modeling. The proposed scheme comprises six major steps: (1) preprocessing of LIDAR data and vector maps, (2) extraction of point clouds that belong to a building, (3) construction of the facets from the point clouds, (4) detection of planar faces, (5) determination of 3-D edges of buildings, and (6) regularization of 3-D edges and building reconstruction. In the preprocessing stage, the height variation of the aboveground objects is extracted by subtracting the surface elevation from the terrain. The polygons for buildings are also obtained from the polylines using the SMS method. Using the vertex locations and rough heights of stories, the point clouds that belong to a building can be selected. Then a triangulated irregular network is built for representing the facets of the point clouds. Segmentation of planar faces is implemented by examining the size and the angles among surface normal vectors. After detection for planar roof faces, 3-D roof edges are determined by intersecting roof planes. Finally, building models are reconstructed after regularization.

Original languageEnglish
Title of host publicationAsian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005
Pages871-877
Number of pages7
Publication statusPublished - 2005 Dec 1
Event26th Asian Conference on Remote Sensing, ACRS 2005 and 2nd Asian Space Conference, ASC - Ha Noi, Viet Nam
Duration: 2005 Nov 72005 Nov 11

Publication series

NameAsian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005
Volume2

Other

Other26th Asian Conference on Remote Sensing, ACRS 2005 and 2nd Asian Space Conference, ASC
CountryViet Nam
CityHa Noi
Period05-11-0705-11-11

Fingerprint

Roofs
Data fusion

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering

Cite this

Chen, L. C., Kuo, C. Y., Rau, J-Y., & Hsieh, C. H. (2005). Fusion of LIDAR data and large-scale vector maps for building reconstruction. In Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005 (pp. 871-877). (Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005; Vol. 2).
Chen, Liang Chien ; Kuo, Chih Yi ; Rau, Jiann-Yeou ; Hsieh, Chi Heng. / Fusion of LIDAR data and large-scale vector maps for building reconstruction. Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005. 2005. pp. 871-877 (Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005).
@inproceedings{06efe653b0f44419a8ed785be8093d15,
title = "Fusion of LIDAR data and large-scale vector maps for building reconstruction",
abstract = "LIDAR data contains plenty of height information, while vector maps preserve accurate building boundaries. From the viewpoint of data fusion, we integrate LIDAR data and large-scale vector maps to perform building modeling. The proposed scheme comprises six major steps: (1) preprocessing of LIDAR data and vector maps, (2) extraction of point clouds that belong to a building, (3) construction of the facets from the point clouds, (4) detection of planar faces, (5) determination of 3-D edges of buildings, and (6) regularization of 3-D edges and building reconstruction. In the preprocessing stage, the height variation of the aboveground objects is extracted by subtracting the surface elevation from the terrain. The polygons for buildings are also obtained from the polylines using the SMS method. Using the vertex locations and rough heights of stories, the point clouds that belong to a building can be selected. Then a triangulated irregular network is built for representing the facets of the point clouds. Segmentation of planar faces is implemented by examining the size and the angles among surface normal vectors. After detection for planar roof faces, 3-D roof edges are determined by intersecting roof planes. Finally, building models are reconstructed after regularization.",
author = "Chen, {Liang Chien} and Kuo, {Chih Yi} and Jiann-Yeou Rau and Hsieh, {Chi Heng}",
year = "2005",
month = "12",
day = "1",
language = "English",
isbn = "9781604237511",
series = "Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005",
pages = "871--877",
booktitle = "Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005",

}

Chen, LC, Kuo, CY, Rau, J-Y & Hsieh, CH 2005, Fusion of LIDAR data and large-scale vector maps for building reconstruction. in Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005. Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005, vol. 2, pp. 871-877, 26th Asian Conference on Remote Sensing, ACRS 2005 and 2nd Asian Space Conference, ASC, Ha Noi, Viet Nam, 05-11-07.

Fusion of LIDAR data and large-scale vector maps for building reconstruction. / Chen, Liang Chien; Kuo, Chih Yi; Rau, Jiann-Yeou; Hsieh, Chi Heng.

Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005. 2005. p. 871-877 (Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005; Vol. 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Fusion of LIDAR data and large-scale vector maps for building reconstruction

AU - Chen, Liang Chien

AU - Kuo, Chih Yi

AU - Rau, Jiann-Yeou

AU - Hsieh, Chi Heng

PY - 2005/12/1

Y1 - 2005/12/1

N2 - LIDAR data contains plenty of height information, while vector maps preserve accurate building boundaries. From the viewpoint of data fusion, we integrate LIDAR data and large-scale vector maps to perform building modeling. The proposed scheme comprises six major steps: (1) preprocessing of LIDAR data and vector maps, (2) extraction of point clouds that belong to a building, (3) construction of the facets from the point clouds, (4) detection of planar faces, (5) determination of 3-D edges of buildings, and (6) regularization of 3-D edges and building reconstruction. In the preprocessing stage, the height variation of the aboveground objects is extracted by subtracting the surface elevation from the terrain. The polygons for buildings are also obtained from the polylines using the SMS method. Using the vertex locations and rough heights of stories, the point clouds that belong to a building can be selected. Then a triangulated irregular network is built for representing the facets of the point clouds. Segmentation of planar faces is implemented by examining the size and the angles among surface normal vectors. After detection for planar roof faces, 3-D roof edges are determined by intersecting roof planes. Finally, building models are reconstructed after regularization.

AB - LIDAR data contains plenty of height information, while vector maps preserve accurate building boundaries. From the viewpoint of data fusion, we integrate LIDAR data and large-scale vector maps to perform building modeling. The proposed scheme comprises six major steps: (1) preprocessing of LIDAR data and vector maps, (2) extraction of point clouds that belong to a building, (3) construction of the facets from the point clouds, (4) detection of planar faces, (5) determination of 3-D edges of buildings, and (6) regularization of 3-D edges and building reconstruction. In the preprocessing stage, the height variation of the aboveground objects is extracted by subtracting the surface elevation from the terrain. The polygons for buildings are also obtained from the polylines using the SMS method. Using the vertex locations and rough heights of stories, the point clouds that belong to a building can be selected. Then a triangulated irregular network is built for representing the facets of the point clouds. Segmentation of planar faces is implemented by examining the size and the angles among surface normal vectors. After detection for planar roof faces, 3-D roof edges are determined by intersecting roof planes. Finally, building models are reconstructed after regularization.

UR - http://www.scopus.com/inward/record.url?scp=84866093658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866093658&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781604237511

T3 - Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005

SP - 871

EP - 877

BT - Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005

ER -

Chen LC, Kuo CY, Rau J-Y, Hsieh CH. Fusion of LIDAR data and large-scale vector maps for building reconstruction. In Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005. 2005. p. 871-877. (Asian Association on Remote Sensing - 26th Asian Conference on Remote Sensing and 2nd Asian Space Conference, ACRS 2005).