Building Footprint Extraction with Graph Convolutional Network

Yilei Shi; Qinyu Li; Xiaoxiang Zhu

doi:10.1109/IGARSS.2019.8898764

Building Footprint Extraction with Graph Convolutional Network

Yilei Shi, Qinyu Li, Xiaoxiang Zhu

Chair of Data Science in Earth Observation

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

5 Scopus citations

Abstract

Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes. Recent developments in deep convolutional neural networks (DCNNs) have enabled accurate pixel-level labeling tasks. One central issue remains, which is the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to progressive downsampling. In this work, we have proposed a end-to-end framework to overcome this issue, which uses the graph convolutional network (GCN) for building footprint extraction task. Our proposed framework outperforms state-of-the-art methods.

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	5136-5139
Number of pages	4
ISBN (Electronic)	9781538691540
DOIs	https://doi.org/10.1109/IGARSS.2019.8898764
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/Territory	Japan
City	Yokohama
Period	28/07/19 → 2/08/19

Keywords

Building footprint
Deep convolutional neural networks
Graph convolutional network

Access to Document

10.1109/IGARSS.2019.8898764

Cite this

Shi, Y., Li, Q., & Zhu, X. (2019). Building Footprint Extraction with Graph Convolutional Network. In 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings (pp. 5136-5139). Article 8898764 (International Geoscience and Remote Sensing Symposium (IGARSS)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2019.8898764

@inproceedings{370cf9759bba4ec0ae280753fcdc5e32,

title = "Building Footprint Extraction with Graph Convolutional Network",

abstract = "Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes. Recent developments in deep convolutional neural networks (DCNNs) have enabled accurate pixel-level labeling tasks. One central issue remains, which is the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to progressive downsampling. In this work, we have proposed a end-to-end framework to overcome this issue, which uses the graph convolutional network (GCN) for building footprint extraction task. Our proposed framework outperforms state-of-the-art methods.",

keywords = "Building footprint, Deep convolutional neural networks, Graph convolutional network",

author = "Yilei Shi and Qinyu Li and Xiaoxiang Zhu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2019",

month = jul,

doi = "10.1109/IGARSS.2019.8898764",

language = "English",

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

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

pages = "5136--5139",

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

}

Shi, Y, Li, Q & Zhu, X 2019, Building Footprint Extraction with Graph Convolutional Network. in 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings., 8898764, International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., pp. 5136-5139, 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 28/07/19. https://doi.org/10.1109/IGARSS.2019.8898764

Building Footprint Extraction with Graph Convolutional Network. / Shi, Yilei; Li, Qinyu; Zhu, Xiaoxiang.
2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 5136-5139 8898764 (International Geoscience and Remote Sensing Symposium (IGARSS)).

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

TY - GEN

T1 - Building Footprint Extraction with Graph Convolutional Network

AU - Shi, Yilei

AU - Li, Qinyu

AU - Zhu, Xiaoxiang

PY - 2019/7

Y1 - 2019/7

N2 - Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes. Recent developments in deep convolutional neural networks (DCNNs) have enabled accurate pixel-level labeling tasks. One central issue remains, which is the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to progressive downsampling. In this work, we have proposed a end-to-end framework to overcome this issue, which uses the graph convolutional network (GCN) for building footprint extraction task. Our proposed framework outperforms state-of-the-art methods.

AB - Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes. Recent developments in deep convolutional neural networks (DCNNs) have enabled accurate pixel-level labeling tasks. One central issue remains, which is the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to progressive downsampling. In this work, we have proposed a end-to-end framework to overcome this issue, which uses the graph convolutional network (GCN) for building footprint extraction task. Our proposed framework outperforms state-of-the-art methods.

KW - Building footprint

KW - Deep convolutional neural networks

KW - Graph convolutional network

UR - http://www.scopus.com/inward/record.url?scp=85077707864&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2019.8898764

DO - 10.1109/IGARSS.2019.8898764

M3 - Conference contribution

AN - SCOPUS:85077707864

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 5136

EP - 5139

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Building Footprint Extraction with Graph Convolutional Network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this