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

Matthieu Molinier; Jorma Laaksonen; Seppo Väätäinen; Tuomas Häme

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

Matthieu Molinier, Jorma Laaksonen, Seppo Väätäinen, Tuomas Häme

Helsinki University of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-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 language	English
Title of host publication	ESA-EUSC 2006 Image Information Mining for Security and Intelligence
Subtitle of host publication	Proceedings of meeting held from 27-29 November 2006 in Madrid, Spain.
Publisher	European Space Agency (ESA)
Publication status	Published - 2007
MoE publication type	Not Eligible
Event	4th Conference on Image Information Mining - Torrejon Air Base, Madrid, Spain Duration: 27 Nov 2006 → 29 Nov 2006

Publication series

Series	ESA Conference Proceedings
Number	WPP-274
ISSN	1022-6656

Conference

Conference	4th Conference on Image Information Mining
Country/Territory	Spain
City	Madrid
Period	27/11/06 → 29/11/06

Keywords

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

Access to Document

http://research.ics.aalto.fi/cbir/papers/eusc2006.pdf

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). http://research.ics.aalto.fi/cbir/papers/eusc2006.pdf

Molinier, Matthieu ; Laaksonen, Jorma ; Väätäinen, Seppo et al. / 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.; 4th Conference on Image Information Mining ; Conference date: 27-11-2006 Through 29-11-2006",

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. <http://research.ics.aalto.fi/cbir/papers/eusc2006.pdf>

Self-organising maps for change detection and monitoring of human activity in satellite imagery. / Molinier, Matthieu; Laaksonen, Jorma; Väätäinen, Seppo et al.
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 proceeding › Conference article in proceedings › Scientific › peer-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)

T2 - 4th Conference on Image Information Mining

Y2 - 27 November 2006 through 29 November 2006

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).

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

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this