oru.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0002-0579-7181
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0002-0305-3728
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0002-4001-2087
Örebro University, School of Science and Technology. (Appl Autonomous Sensor Syst (AASS))ORCID iD: 0000-0002-3122-693X
2016 (English)In: Remote Sensing, ISSN 2072-4292, E-ISSN 2072-4292, Vol. 8, no 4, article id 329Article in journal (Refereed) Published
Resource type
Text
Abstract [en]

The availability of high-resolution remote sensing (HRRS) data has opened up the possibility for new interesting applications, such as per-pixel classification of individual objects in greater detail. This paper shows how a convolutional neural network (CNN) can be applied to multispectral orthoimagery and a digital surface model (DSM) of a small city for a full, fast and accurate per-pixel classification. The predicted low-level pixel classes are then used to improve the high-level segmentation. Various design choices of the CNN architecture are evaluated and analyzed. The investigated land area is fully manually labeled into five categories (vegetation, ground, roads, buildings and water), and the classification accuracy is compared to other per-pixel classification works on other land areas that have a similar choice of categories. The results of the full classification and segmentation on selected segments of the map show that CNNs are a viable tool for solving both the segmentation and object recognition task for remote sensing data.

Place, publisher, year, edition, pages
Basel: MDPI AG , 2016. Vol. 8, no 4, article id 329
Keywords [en]
remote sensing, orthoimagery, convolutional neural network, per-pixel classification, segmentation, region merging
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:oru:diva-50501DOI: 10.3390/rs8040329ISI: 000375156500062OAI: oai:DiVA.org:oru-50501DiVA, id: diva2:932023
Funder
Knowledge Foundation, 20140033Available from: 2016-05-31 Created: 2016-05-31 Last updated: 2018-07-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records BETA

Längkvist, MartinKiselev, AndreyAlirezaie, MarjanLoutfi, Amy

Search in DiVA

By author/editor
Längkvist, MartinKiselev, AndreyAlirezaie, MarjanLoutfi, Amy
By organisation
School of Science and Technology
In the same journal
Remote Sensing
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 440 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf