Self-organising maps for change detection and monitoring of human activity in satellite imagery

Matthieu Molinier, Jorma Laaksonen, Seppo Väätäinen, Tuomas Häme

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


Self-Organising 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. Results open a full range of applications, from structure detection to change detection, to be embedded in a same operative system. The framework may be particularly suitable for long-term monitoring of strategic sites.
Original languageEnglish
Title of host publicationESA-EUSC 2006 Image Information Mining for Security and Intelligence
Subtitle of host publicationProceedings of meeting held from 27-29 November 2006 in Madrid, Spain.
PublisherEuropean Space Agency (ESA)
Publication statusPublished - 2007
MoE publication typeNot Eligible
Event4th Conference on Image Information Mining - Torrejon Air Base, Madrid, Spain
Duration: 27 Nov 200629 Nov 2006

Publication series

SeriesESA Conference Proceedings


Conference4th Conference on Image Information Mining


  • content-based information retrieval
  • self-organising maps
  • high resolution satellite images
  • manmade structure detection
  • change detection

Fingerprint Dive into the research topics of 'Self-organising maps for change detection and monitoring of human activity in satellite imagery'. Together they form a unique fingerprint.

Cite this