Improving content-based target and change detection in ALOS PALSAR images with efficient feature selection

Matthieu Molinier; Ville Viitaniemi; Markus Koskela; Jorma Laaksonen; Yrjö Rauste; Anne Lönnqvist; Tuomas Häme

Improving content-based target and change detection in ALOS PALSAR images with efficient feature selection

Matthieu Molinier, Ville Viitaniemi, Markus Koskela, Jorma Laaksonen, Yrjö Rauste, Anne Lönnqvist, 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 quad-polarised ALOS PALSAR 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. Polarimetric features were extracted from the images to allow image indexing. By querying the databases, it was possible to detect target classes, as well as changes between the two 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	Proceedings of ESA-EUSC Symposium 2008 – WPP-278
Number of pages	8
Edition	cd-rom
Publication status	Published - 2008
MoE publication type	Not Eligible

Keywords

content-based information retrieval
self-organising maps
high resolution satellite images
polarimetric spaceborne SAR
change detection

Access to Document

http://users.ics.aalto.fi/markus/esa_eusc2008.pdf

Cite this

@inproceedings{105cf02dc5f54fa3af1423d76c309a62,

title = "Improving content-based target and change detection in ALOS PALSAR images with efficient feature selection",

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 quad-polarised ALOS PALSAR 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. Polarimetric features were extracted from the images to allow image indexing. By querying the databases, it was possible to detect target classes, as well as changes between the two 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, polarimetric spaceborne SAR, change detection",

author = "Matthieu Molinier and Ville Viitaniemi and Markus Koskela and Jorma Laaksonen and Yrj{\"o} Rauste and Anne L{\"o}nnqvist and Tuomas H{\"a}me",

note = "Project code: 7859",

year = "2008",

language = "English",

booktitle = "Proceedings of ESA-EUSC Symposium 2008 – WPP-278",

edition = "cd-rom",

}

Improving content-based target and change detection in ALOS PALSAR images with efficient feature selection. / Molinier, Matthieu; Viitaniemi, Ville; Koskela, Markus et al.
Proceedings of ESA-EUSC Symposium 2008 – WPP-278. cd-rom. ed. 2008.

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

TY - GEN

T1 - Improving content-based target and change detection in ALOS PALSAR images with efficient feature selection

AU - Molinier, Matthieu

AU - Viitaniemi, Ville

AU - Koskela, Markus

AU - Laaksonen, Jorma

AU - Rauste, Yrjö

AU - Lönnqvist, Anne

AU - Häme, Tuomas

N1 - Project code: 7859

PY - 2008

Y1 - 2008

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 quad-polarised ALOS PALSAR 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. Polarimetric features were extracted from the images to allow image indexing. By querying the databases, it was possible to detect target classes, as well as changes between the two 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 quad-polarised ALOS PALSAR 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. Polarimetric features were extracted from the images to allow image indexing. By querying the databases, it was possible to detect target classes, as well as changes between the two 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 - polarimetric spaceborne SAR

KW - change detection

M3 - Conference article in proceedings

BT - Proceedings of ESA-EUSC Symposium 2008 – WPP-278

ER -

Improving content-based target and change detection in ALOS PALSAR images with efficient feature selection

Abstract

Keywords

Access to Document

Fingerprint

Cite this