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

Building Extraction from Remote Sensing Data using fully convolutional Networks

Bittner, Ksenia and Cui, Shiyong and Reinartz, Peter (2017) Building Extraction from Remote Sensing Data using fully convolutional Networks. In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, XLII-1 (W1), pp. 481-486. Copernicus Publications. ISPRS Hannover Workshop: HRIGI 17, 06.-09. Juni 2017, Hannover, Germany. DOI: 10.5194/isprs-archives-XLII-1-W1-481-2017

[img] PDF
1MB

Official URL: http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-1-W1/481/2017/

Abstract

Building detection and footprint extraction are highly demanded for many remote sensing applications. Though most previous works have shown promising results, the automatic extraction of building footprints still remains a nontrivial topic, especially in complex urban areas. Recently developed extensions of the CNN framework made it possible to perform dense pixel-wise classification of input images. Based on these abilities we propose a methodology, which automatically generates a full resolution binary building mask out of a Digital Surface Model (DSM) using a Fully Convolution Network (FCN) architecture. The advantage of using the depth information is that it provides geometrical silhouettes and allows a better separation of buildings from background as well as through its invariance to illumination and color variations. The proposed framework has mainly two steps. Firstly, the FCN is trained on a large set of patches consisting of normalized DSM (nDSM) as inputs and available ground truth building mask as target outputs. Secondly, the generated predictions from FCN are viewed as unary terms for a Fully connected Conditional Random Fields (FCRF), which enables us to create a final binary building mask. A series of experiments demonstrate that our methodology is able to extract accurate building footprints which are close to the buildings original shapes to a high degree. The quantitative and qualitative analysis show the significant improvements of the results in contrast to the multy-layer fully connected network from our previous work.

Item URL in elib:https://elib.dlr.de/112900/
Document Type:Conference or Workshop Item (Speech, Poster)
Title:Building Extraction from Remote Sensing Data using fully convolutional Networks
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Bittner, KseniaKsenia.Bittner (at) dlr.deUNSPECIFIED
Cui, Shiyongshiyong.cui (at) dlr.deUNSPECIFIED
Reinartz, Peterpeter.reinartz (at) dlr.dehttps://orcid.org/0000-0002-8122-1475
Date:2017
Journal or Publication Title:International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Volume:XLII-1
DOI :10.5194/isprs-archives-XLII-1-W1-481-2017
Page Range:pp. 481-486
Editors:
EditorsEmail
UNSPECIFIEDISPRS Org.
Publisher:Copernicus Publications
Status:Published
Keywords:deep learning, DSM, fully convolutional networks, building footprint, binary classification, fully connected CRF
Event Title:ISPRS Hannover Workshop: HRIGI 17
Event Location:Hannover, Germany
Event Type:international Conference
Event Dates:06.-09. Juni 2017
Organizer:ISPRS
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, Vorhaben Optical Remote Sensing
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By:INVALID USER
Deposited On:30 Jun 2017 13:29
Last Modified:31 Jul 2019 20:10

Repository Staff Only: item control page

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