Self-organizing map application for retrieval of man-made structures in remote sensing data

Matthieu Molinier, Jorma Laaksonen, Jussi Ahola, Tuomas Häme

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

Abstract

Self-Organizing Maps (SOMs) have been successfully applied to content-based image retrieval (CBIR). In this study, we investigate the potential of PicSOM, an image database browsing system, applied to remote sensing images. Databases of small images were artificially created, either from a single satellite image for object detection, or two satellite images when considering change detection. By visually querying those databases, it was possible to detect targets like houses, roads or man-made structures, as well as changes between two QuickBird images. Preliminary results were encouraging, and open a full range of applications, from structure detection to change detection, to be embedded in a same operative system.
Original languageEnglish
Title of host publicationESA-EUSC 2005: Image Information Mining - Theory and Applicaiton to Earth Observation
Subtitle of host publicationProceedings of the workshop
PublisherEuropean Space Agency ESA
Number of pages8
Publication statusPublished - 2006
MoE publication typeNot Eligible
EventESA-EUSC Workshop on Image Information Mining - Theory and Applications to Earth Observation - Frascati, Italy
Duration: 5 Oct 20057 Oct 2005

Publication series

SeriesESA Conference Proceedings
NumberESA WPP-257
ISSN1022-6656

Workshop

WorkshopESA-EUSC Workshop on Image Information Mining - Theory and Applications to Earth Observation
CountryItaly
CityFrascati
Period5/10/057/10/05

    Fingerprint

Keywords

  • content-based information retrieval
  • self-organizing
  • maps
  • high resolution satellite images
  • man-made structure detection
  • change detection

Cite this

Molinier, M., Laaksonen, J., Ahola, J., & Häme, T. (2006). Self-organizing map application for retrieval of man-made structures in remote sensing data. In ESA-EUSC 2005: Image Information Mining - Theory and Applicaiton to Earth Observation: Proceedings of the workshop European Space Agency ESA. ESA Conference Proceedings, No. ESA WPP-257