Header

UZH-Logo

Maintenance Infos

Learning class- and location-specific priors for urban semantic labeling with CNNs


Kellenberger, Benjamin; Volpi, Michele; Tuia, Devis (2017). Learning class- and location-specific priors for urban semantic labeling with CNNs. In: 2017 Joint Urban Remote Sensing Event (JURSE), Dubai (UAE), 6 March 2017 - 8 March 2017.

Abstract

This paper addresses the problem of semantic image labeling of urban remote sensing images into land cover maps. We exploit the prior knowledge that cities are composed of comparable spatial arrangements of urban objects, such as buildings. To do so, we cluster OpenStreetMap (OSM) building footprints into groups with similar local statistics, corresponding to different types of urban zones. We use the per-cluster expected building fraction to correct for over- and underrepresentation of classes predicted by a Convolutional Neural Network (CNN), using a Conditional Random Field (CRF). Results indicate a substantial improvement in both numerical and visual accuracy of the labeled maps.

Abstract

This paper addresses the problem of semantic image labeling of urban remote sensing images into land cover maps. We exploit the prior knowledge that cities are composed of comparable spatial arrangements of urban objects, such as buildings. To do so, we cluster OpenStreetMap (OSM) building footprints into groups with similar local statistics, corresponding to different types of urban zones. We use the per-cluster expected building fraction to correct for over- and underrepresentation of classes predicted by a Convolutional Neural Network (CNN), using a Conditional Random Field (CRF). Results indicate a substantial improvement in both numerical and visual accuracy of the labeled maps.

Statistics

Citations

Altmetrics

Downloads

1 download since deposited on 03 Nov 2017
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), not_refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
Dewey Decimal Classification:910 Geography & travel
Language:English
Event End Date:8 March 2017
Deposited On:03 Nov 2017 10:25
Last Modified:29 Jul 2018 05:51
Publisher:IEEE
ISBN:978-1-5090-5808-2
OA Status:Closed
Publisher DOI:https://doi.org/10.1109/JURSE.2017.7924537
Official URL:http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7919506

Download