DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Semantic segmentation by gated graph convolutional neural network with deep structured feature embedding

Shi, Yilei and Li, Qingyu and Zhu, Xiao Xiang (2020) Semantic segmentation by gated graph convolutional neural network with deep structured feature embedding. ISPRS Journal of Photogrammetry and Remote Sensing, 159, pp. 184-197. Elsevier. DOI: 10.1016/j.isprsjprs.2019.11.004 ISSN 0924-2716

[img] PDF - Registered users only until January 2021 - Published version

Official URL: https://www.sciencedirect.com/science/article/pii/S092427161930259X


Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity ofbuilding shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural networks (DCNNs) has made accurate pixel-level classification tasks possible. Yet onecentral issue remains: the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to their progressive down-sampling. Hence, we introduce ageneric framework to overcome the issue, integrating the graph convolutional network (GCN) and deep struc-tured feature embedding (DSFE) into an end-to-end workflow. Furthermore, instead of using a classic graphconvolutional neural network, we propose a gated graph convolutional network, which enables the refinement of weak and coarse semantic predictions to generate sharp borders and fine-grained pixel-level classification.Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks. Our proposed framework with the new GCN architectureoutperforms state-of-the-art approaches. Although our main task in this work is building footprint extraction, theproposed method can be generally applied to other binary or multi-label segmentation tasks.

Item URL in elib:https://elib.dlr.de/132448/
Document Type:Article
Title:Semantic segmentation by gated graph convolutional neural network with deep structured feature embedding
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Zhu, Xiao Xiangxiao.zhu (at) dlr.deUNSPECIFIED
Date:January 2020
Journal or Publication Title:ISPRS Journal of Photogrammetry and Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
DOI :10.1016/j.isprsjprs.2019.11.004
Page Range:pp. 184-197
Keywords:building extraction, semantic segmentation, graph model, gated convoluational neural networks.
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Hong, Danfeng
Deposited On:06 Dec 2019 16:50
Last Modified:06 Dec 2019 16:50

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.