Land use classification using deep multitask networks

J.R. Bergado*, C. Persello, A. Stein

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

12 Downloads (Pure)

Abstract

Updated information on urban land use allows city planners and decision makers to conduct large scale monitoring of urban areas for sustainable urban growth. Remote sensing data and classification methods offer an efficient and reliable way to update such land use maps. Features extracted from land cover maps are helpful on performing a land use classification task. Such prior information can be embedded in the design of a deep learning based land use classifier by applying a multitask learning setup-simultaneously solving a land use and a land cover classification task. In this study, we explore a fully convolutional multitask network to classify urban land use from very high resolution (VHR) imagery. We experimented with three different setups of the fully convolutional network and compared it against a baseline random forest classifier. The first setup is a standard network only predicting the land use class of each pixel in the image. The second setup is a multitask network that concatenates the land use and land cover class labels in the same output layer of the network while the other setup accept as an input the land cover predictions, predicted by a subpart of the network, concatenated to the original input image patches. The two deep multitask networks outperforms the other two classifiers by at least 30% in average F1-score.

Original languageEnglish
Title of host publicationInt. Arch. Photogramm. Remote Sens. Spatial Inf. Sci
EditorsN. Paparoditis, C. Mallet, F. Lafarge, J. Jiang, A. Shaker, H. Zhang, X. Liang, B. Osmanoglu, U. Soergel, E. Honkavaara, M. Scaioni, J. Zhang, A, Peled, L. Wu, R. Li, M. Yoshimura, K. Di, O. Altan, H.M. Abdulmuttalib, F.S. Faruque
Place of PublicationNice
PublisherInternational Society for Photogrammetry and Remote Sensing (ISPRS)
Pages17-21
Number of pages5
Volume43
EditionB3
DOIs
Publication statusPublished - 6 Aug 2020
EventXXIVth ISPRS Congress 2020 - Virtual Event, Nice, France
Duration: 4 Jul 202010 Jul 2020
Conference number: 24
http://www.isprs2020-nice.com

Publication series

NameInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
PublisherCopernicus
ISSN (Print)1682-1750

Conference

ConferenceXXIVth ISPRS Congress 2020
Abbreviated titleISPRS 2020
CountryFrance
CityNice
Period4/07/2010/07/20
Internet address

Keywords

  • Convolutional Networks
  • Land Use Classification
  • Multitask Learning
  • VHR Imagery

Fingerprint Dive into the research topics of 'Land use classification using deep multitask networks'. Together they form a unique fingerprint.

Cite this