uu.seUppsala universitets publikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Automatic Water Body Extraction From Remote Sensing Images Using Entropy
Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion.ORCID-id: 0000-0003-0085-5829
2015 (Engelska)Ingår i: SGEM2015 Conference Proceedings, 2015, Vol. 2, s. 517-524Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This research focuses on automatic extraction of river banks and other inland waters from remote sensing images. There are no up to date accessible databases of rivers and most of other waters objects for modelling purposes. The main reason for that is that some regions are hard to access with the traditional ground through techniques and thus the boundary of river banks are uncertain in many geographical positions. The other reason is the limitations of widely applied method for extraction of water bodies called normalized-difference water index (NDWI). There is a novel approach to extract water bodies, which is based on pixel level variability or entropy, however, the methods work somewhat satisfactory on high spatial resolution images, there is no verification of the method performance on moderate or low resolution images. Problems encounter identification of mixed water pixels and e.g. roads, which are built in attachment to river banks and thus can be classified as rivers. In this work we propose an automatic extraction of river banks using image entropy, combined with NDWI identification. In this study only moderate spatial resolution Landsat TM are tested. Areas of interest include both major river banks and inland lakes. Calculating entropy on such poor spatial resolution images will lead to misinterpretation of water bodies, which all exhibits the same small variation of pixel values as e.g. some open or urban areas. Image entropy thus is calculated with the modification that involves the incorporation of local normalization index or variability coefficient. NDWI will produce an image where clear water exhibits large difference comparing to other land features. We are presenting an algorithm that uses an NDWI prior to entropy processing, so that bands used to calculate it, are chosen in clear connection to water body features that are clearly discernible.As a result we visualize a clear segmentation of the water bodies from the remote sensing images and verify the coordinates with a given geographic reference.

Ort, förlag, år, upplaga, sidor
2015. Vol. 2, s. 517-524
Serie
International Multidisciplinary Scientific GeoConference-SGEM, ISSN 1314-2704
Nyckelord [en]
water; NDWI; Entropy; extraction
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
URN: urn:nbn:se:uu:diva-266903DOI: 10.5593/SGEM2015/B21/S8.064ISI: 000371599500064ISBN: 9786197105346 (tryckt)OAI: oai:DiVA.org:uu-266903DiVA, id: diva2:869180
Konferens
15th International Multidisciplinary Scientific GeoConference SGEM 2015
Tillgänglig från: 2015-09-15 Skapad: 2015-11-13 Senast uppdaterad: 2018-01-10Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Personposter BETA

Seipel, Stefan

Sök vidare i DiVA

Av författaren/redaktören
Seipel, Stefan
Av organisationen
Avdelningen för visuell information och interaktionBildanalys och människa-datorinteraktion
Datorseende och robotik (autonoma system)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 506 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf