A self-organizing map framework for detection of man-made structures and changes in satellite imagery

Matthieu Molinier; Jorma Laaksonen; Tuomas Häme

doi:10.1109/IGARSS.2006.5

A self-organizing map framework for detection of man-made structures and changes in satellite imagery

Matthieu Molinier^*, Jorma Laaksonen, Tuomas Häme

^*Corresponding author for this work

Aalto University

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

Content-based querying allows efficient retrieval of images based on the information they contain, rather than acquisition date or geographical extent. We extend the potential of a content-based image retrieval (CBIR) system based on Self-Organizing Maps (SOMs), to the analysis of remote sensing data. A database was artificially created by splitting each satellite image to be analyzed into small images. After training the CBIR system on this imagelet database, both interactive and off-line queries were made to detect man-made structures, as well as changes. Experimental results suggest that this new approach is suitable for analyzing very high-resolution optical satellite imagery. Possible applications include interactive detection of man-made structures and supervised monitoring of sensitive sites.

Original language	English
Title of host publication	2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS
Pages	53 - 56
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2006.5
Publication status	Published - 1 Dec 2006
MoE publication type	A4 Article in a conference publication
Event	2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS - Denver, CO, United States Duration: 31 Jul 2006 → 4 Aug 2006

Conference

Conference	2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS
Abbreviated title	IGARSS 2006
Country/Territory	United States
City	Denver, CO
Period	31/07/06 → 4/08/06

Keywords

Change detection
Self-Organizing Maps

Access to Document

10.1109/IGARSS.2006.5

Cite this

@inproceedings{7bbd7493e1f04c50b6385a7e7d9d0c05,

title = "A self-organizing map framework for detection of man-made structures and changes in satellite imagery",

abstract = "Content-based querying allows efficient retrieval of images based on the information they contain, rather than acquisition date or geographical extent. We extend the potential of a content-based image retrieval (CBIR) system based on Self-Organizing Maps (SOMs), to the analysis of remote sensing data. A database was artificially created by splitting each satellite image to be analyzed into small images. After training the CBIR system on this imagelet database, both interactive and off-line queries were made to detect man-made structures, as well as changes. Experimental results suggest that this new approach is suitable for analyzing very high-resolution optical satellite imagery. Possible applications include interactive detection of man-made structures and supervised monitoring of sensitive sites.",

keywords = "Change detection, Self-Organizing Maps",

author = "Matthieu Molinier and Jorma Laaksonen and Tuomas H{\"a}me",

year = "2006",

month = dec,

day = "1",

doi = "10.1109/IGARSS.2006.5",

language = "English",

isbn = "978-0-78039510-7",

pages = "53 -- 56",

booktitle = "2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS",

note = "2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS, IGARSS 2006 ; Conference date: 31-07-2006 Through 04-08-2006",

}

Molinier, M, Laaksonen, J & Häme, T 2006, A self-organizing map framework for detection of man-made structures and changes in satellite imagery. in 2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS., 4241152, pp. 53 - 56, 2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS, Denver, CO, United States, 31/07/06. https://doi.org/10.1109/IGARSS.2006.5

A self-organizing map framework for detection of man-made structures and changes in satellite imagery. / Molinier, Matthieu; Laaksonen, Jorma; Häme, Tuomas.
2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS. 2006. p. 53 - 56 4241152.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - A self-organizing map framework for detection of man-made structures and changes in satellite imagery

AU - Molinier, Matthieu

AU - Laaksonen, Jorma

AU - Häme, Tuomas

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Content-based querying allows efficient retrieval of images based on the information they contain, rather than acquisition date or geographical extent. We extend the potential of a content-based image retrieval (CBIR) system based on Self-Organizing Maps (SOMs), to the analysis of remote sensing data. A database was artificially created by splitting each satellite image to be analyzed into small images. After training the CBIR system on this imagelet database, both interactive and off-line queries were made to detect man-made structures, as well as changes. Experimental results suggest that this new approach is suitable for analyzing very high-resolution optical satellite imagery. Possible applications include interactive detection of man-made structures and supervised monitoring of sensitive sites.

AB - Content-based querying allows efficient retrieval of images based on the information they contain, rather than acquisition date or geographical extent. We extend the potential of a content-based image retrieval (CBIR) system based on Self-Organizing Maps (SOMs), to the analysis of remote sensing data. A database was artificially created by splitting each satellite image to be analyzed into small images. After training the CBIR system on this imagelet database, both interactive and off-line queries were made to detect man-made structures, as well as changes. Experimental results suggest that this new approach is suitable for analyzing very high-resolution optical satellite imagery. Possible applications include interactive detection of man-made structures and supervised monitoring of sensitive sites.

KW - Change detection

KW - Self-Organizing Maps

UR - http://www.scopus.com/inward/record.url?scp=34948864334&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2006.5

DO - 10.1109/IGARSS.2006.5

M3 - Conference article in proceedings

AN - SCOPUS:34948864334

SN - 978-0-78039510-7

SP - 53

EP - 56

BT - 2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS

T2 - 2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS

Y2 - 31 July 2006 through 4 August 2006

ER -

A self-organizing map framework for detection of man-made structures and changes in satellite imagery

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this