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

Abstract

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
NumberWPP-274
ISSN1022-6656

Conference

Conference4th Conference on Image Information Mining
CountrySpain
CityMadrid
Period27/11/0629/11/06

Fingerprint

satellite imagery
human activity
monitoring
QuickBird
browsing
detection
road
remote sensing
satellite image

Keywords

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

Cite this

Molinier, M., Laaksonen, J., Väätäinen, S., & Häme, T. (2007). Self-organising maps for change detection and monitoring of human activity in satellite imagery. In ESA-EUSC 2006 Image Information Mining for Security and Intelligence: Proceedings of meeting held from 27-29 November 2006 in Madrid, Spain. European Space Agency ESA. ESA Conference Proceedings, No. WPP-274
Molinier, Matthieu ; Laaksonen, Jorma ; Väätäinen, Seppo ; Häme, Tuomas. / Self-organising maps for change detection and monitoring of human activity in satellite imagery. ESA-EUSC 2006 Image Information Mining for Security and Intelligence: Proceedings of meeting held from 27-29 November 2006 in Madrid, Spain.. European Space Agency ESA, 2007. (ESA Conference Proceedings; No. WPP-274).
@inproceedings{d8ce5dd1f96a4b9b9af1571df9dcee73,
title = "Self-organising maps for change detection and monitoring of human activity in satellite imagery",
abstract = "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.",
keywords = "content-based information retrieval, self-organising maps, high resolution satellite images, manmade structure detection, change detection",
author = "Matthieu Molinier and Jorma Laaksonen and Seppo V{\"a}{\"a}t{\"a}inen and Tuomas H{\"a}me",
note = "Self-archived in Aalto.",
year = "2007",
language = "English",
series = "ESA Conference Proceedings",
publisher = "European Space Agency ESA",
number = "WPP-274",
booktitle = "ESA-EUSC 2006 Image Information Mining for Security and Intelligence",
address = "France",

}

Molinier, M, Laaksonen, J, Väätäinen, S & Häme, T 2007, Self-organising maps for change detection and monitoring of human activity in satellite imagery. in ESA-EUSC 2006 Image Information Mining for Security and Intelligence: Proceedings of meeting held from 27-29 November 2006 in Madrid, Spain.. European Space Agency ESA, ESA Conference Proceedings, no. WPP-274, 4th Conference on Image Information Mining, Madrid, Spain, 27/11/06.

Self-organising maps for change detection and monitoring of human activity in satellite imagery. / Molinier, Matthieu; Laaksonen, Jorma; Väätäinen, Seppo; Häme, Tuomas.

ESA-EUSC 2006 Image Information Mining for Security and Intelligence: Proceedings of meeting held from 27-29 November 2006 in Madrid, Spain.. European Space Agency ESA, 2007. (ESA Conference Proceedings; No. WPP-274).

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

TY - GEN

T1 - Self-organising maps for change detection and monitoring of human activity in satellite imagery

AU - Molinier, Matthieu

AU - Laaksonen, Jorma

AU - Väätäinen, Seppo

AU - Häme, Tuomas

N1 - Self-archived in Aalto.

PY - 2007

Y1 - 2007

N2 - 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.

AB - 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.

KW - content-based information retrieval

KW - self-organising maps

KW - high resolution satellite images

KW - manmade structure detection

KW - change detection

M3 - Conference article in proceedings

T3 - ESA Conference Proceedings

BT - ESA-EUSC 2006 Image Information Mining for Security and Intelligence

PB - European Space Agency ESA

ER -

Molinier M, Laaksonen J, Väätäinen S, Häme T. Self-organising maps for change detection and monitoring of human activity in satellite imagery. In ESA-EUSC 2006 Image Information Mining for Security and Intelligence: Proceedings of meeting held from 27-29 November 2006 in Madrid, Spain.. European Space Agency ESA. 2007. (ESA Conference Proceedings; No. WPP-274).