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

Semantic Segmentation of Aerial Images with an Ensemble of CNSS

Marmanis, Dimitrios and Wegner, Jan D. and Galliani, Silvano and Schindler, K. and Datcu, Mihai and Stilla, U. (2016) Semantic Segmentation of Aerial Images with an Ensemble of CNSS. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, III-3, pp. 473-480. Copernicus Publications. ISPRS Congress, 12.-19. Juli 2016, Prag, Tschechien. DOI: 10.5194/isprsannals-III-3-473-2016

[img] PDF
1MB

Official URL: http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/III-3/473/2016/

Abstract

This paper describes a deep learning approach to semantic segmentation of very high resolution (aerial) images. Deep neural architectures hold the promise of end-to-end learning from raw images, making heuristic feature design obsolete. Over the last decade this idea has seen a revival, and in recent years deep convolutional neural networks (CNNs) have emerged as the method of choice for a range of image interpretation tasks like visual recognition and object detection. Still, standard CNNs do not lend themselves to per-pixel semantic segmentation, mainly because one of their fundamental principles is to gradually aggregate information over larger and larger image regions, making it hard to disentangle contributions from different pixels. Very recently two extensions of the CNN framework have made it possible to trace the semantic information back to a precise pixel position: deconvolutional network layers undo the spatial downsampling, and Fully Convolution Networks (FCNs) modify the fully connected classification layers of the network in such a way that the location of individual activations remains explicit. We design a FCN which takes as input intensity and range data and, with the help of aggressive deconvolution and recycling of early network layers, converts them into a pixelwise classification at full resolution. We discuss design choices and intricacies of such a network, and demonstrate that an ensemble of several networks achieves excellent results on challenging data such as the ISPRS semantic labeling benchmark, using only the raw data as input.

Item URL in elib:https://elib.dlr.de/108960/
Document Type:Conference or Workshop Item (Speech)
Title:Semantic Segmentation of Aerial Images with an Ensemble of CNSS
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Marmanis, Dimitriosdimitrios.marmanis (at) dlr.deUNSPECIFIED
Wegner, Jan D.jan.wegner (at) geod.baug.ethz.chUNSPECIFIED
Galliani, Silvanosilvano.galliani (at) geod.baug.ethz.chUNSPECIFIED
Schindler, K.schindler (at) geod.baug.ethz.chUNSPECIFIED
Datcu, Mihaimihai.datcu (at) dlr.deUNSPECIFIED
Stilla, U.stilla (at) tum.deUNSPECIFIED
Date:2016
Journal or Publication Title:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Volume:III-3
DOI :10.5194/isprsannals-III-3-473-2016
Page Range:pp. 473-480
Editors:
EditorsEmail
Halounova, L.UNSPECIFIED
Schindler, K.UNSPECIFIED
Limpouch, A.UNSPECIFIED
Šafář, V.UNSPECIFIED
Pajdla, T.UNSPECIFIED
Mayer, H.UNSPECIFIED
Oude Elberink, S.UNSPECIFIED
Mallet, C.UNSPECIFIED
Rottensteiner, F.UNSPECIFIED
Skaloud, J.UNSPECIFIED
Stilla, U.UNSPECIFIED
Brédif, M.UNSPECIFIED
Publisher:Copernicus Publications
Status:Published
Keywords:semantic segmentation
Event Title:ISPRS Congress
Event Location:Prag, Tschechien
Event Type:international Conference
Event Dates:12.-19. Juli 2016
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
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By:INVALID USER
Deposited On:09 Dec 2016 13:53
Last Modified:31 Jul 2019 20:06

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.