PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

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 and Tuomas Häme
In: ESA-EUSC 2008: Image Information Mining(2008).


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.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:4358
Deposited By:Ville Viitaniemi
Deposited On:24 March 2009