Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data

Tee Ann Teo

doi:10.1109/IGARSS.2019.8897810

Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data

Tee Ann Teo^*

^*Corresponding author for this work

Department of Civil Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

A three-dimensional building model is an important geospatial information for a smart city. The objective of this study is to reconstruct OGC CityGML LOD1 prismatic building models from 3D lidar points automatically. A deep learning approach (i.e. Fully Convolutional Network, FCN) is developed to detect initial building regions for lidar data. After refinement, the building boundary needs regularization to reshape the irregular boundary into a regular building primitive. Finally, a 3D plane fitting is applied to shape the rooftop using lidar points inside building primitive. The test data was an urban area with the size of 1800m by 1200m. The lidar point density was 4 pt/m². The experimental result indicated that the proposed method automatically reconstruct the LOD1 block model from lidar data. The accuracy of building detection reached 72% using lidar object height and intensity. The reconstruction showed high similarity with reference LOD1 building model.

Original language	English
Title of host publication	2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	86-89
Number of pages	4
ISBN (Electronic)	9781538691540
DOIs	https://doi.org/10.1109/IGARSS.2019.8897810
State	Published - Jul 2019
Event	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan Duration: 28 Jul 2019 → 2 Aug 2019

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Country	Japan
City	Yokohama
Period	28/07/19 → 2/08/19

Keywords

3D building model
CityGML LOD1
deep learning
lidar.

UN SDGs

This output contributes to the following Sustainable Development Goal(s)

Access to Document

10.1109/IGARSS.2019.8897810

Fingerprint Dive into the research topics of 'Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data'. Together they form a unique fingerprint.

Cite this

Teo, T. A. (2019). Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings (pp. 86-89). [8897810] (International Geoscience and Remote Sensing Symposium (IGARSS)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2019.8897810

@inproceedings{ee532cf6aa194b84b8be4a8df5ce21ea,

title = "Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data",

abstract = "A three-dimensional building model is an important geospatial information for a smart city. The objective of this study is to reconstruct OGC CityGML LOD1 prismatic building models from 3D lidar points automatically. A deep learning approach (i.e. Fully Convolutional Network, FCN) is developed to detect initial building regions for lidar data. After refinement, the building boundary needs regularization to reshape the irregular boundary into a regular building primitive. Finally, a 3D plane fitting is applied to shape the rooftop using lidar points inside building primitive. The test data was an urban area with the size of 1800m by 1200m. The lidar point density was 4 pt/m2. The experimental result indicated that the proposed method automatically reconstruct the LOD1 block model from lidar data. The accuracy of building detection reached 72% using lidar object height and intensity. The reconstruction showed high similarity with reference LOD1 building model.",

keywords = "3D building model, CityGML LOD1, deep learning, lidar.",

author = "Teo, {Tee Ann}",

year = "2019",

month = jul,

doi = "10.1109/IGARSS.2019.8897810",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "86--89",

booktitle = "2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings",

address = "United States",

note = "null ; Conference date: 28-07-2019 Through 02-08-2019",

}

Teo, TA 2019, Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data. in 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings., 8897810, International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., pp. 86-89, 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 28/07/19. https://doi.org/10.1109/IGARSS.2019.8897810

Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data. / Teo, Tee Ann.

2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 86-89 8897810 (International Geoscience and Remote Sensing Symposium (IGARSS)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data

AU - Teo, Tee Ann

PY - 2019/7

Y1 - 2019/7

N2 - A three-dimensional building model is an important geospatial information for a smart city. The objective of this study is to reconstruct OGC CityGML LOD1 prismatic building models from 3D lidar points automatically. A deep learning approach (i.e. Fully Convolutional Network, FCN) is developed to detect initial building regions for lidar data. After refinement, the building boundary needs regularization to reshape the irregular boundary into a regular building primitive. Finally, a 3D plane fitting is applied to shape the rooftop using lidar points inside building primitive. The test data was an urban area with the size of 1800m by 1200m. The lidar point density was 4 pt/m2. The experimental result indicated that the proposed method automatically reconstruct the LOD1 block model from lidar data. The accuracy of building detection reached 72% using lidar object height and intensity. The reconstruction showed high similarity with reference LOD1 building model.

AB - A three-dimensional building model is an important geospatial information for a smart city. The objective of this study is to reconstruct OGC CityGML LOD1 prismatic building models from 3D lidar points automatically. A deep learning approach (i.e. Fully Convolutional Network, FCN) is developed to detect initial building regions for lidar data. After refinement, the building boundary needs regularization to reshape the irregular boundary into a regular building primitive. Finally, a 3D plane fitting is applied to shape the rooftop using lidar points inside building primitive. The test data was an urban area with the size of 1800m by 1200m. The lidar point density was 4 pt/m2. The experimental result indicated that the proposed method automatically reconstruct the LOD1 block model from lidar data. The accuracy of building detection reached 72% using lidar object height and intensity. The reconstruction showed high similarity with reference LOD1 building model.

KW - 3D building model

KW - CityGML LOD1

KW - deep learning

KW - lidar.

UR - http://www.scopus.com/inward/record.url?scp=85077703045&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2019.8897810

DO - 10.1109/IGARSS.2019.8897810

M3 - Conference contribution

AN - SCOPUS:85077703045

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 86

EP - 89

BT - 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 28 July 2019 through 2 August 2019

ER -

Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Cite this