This FOURTH CONFERENCE on IMAGE INFORMATION MINING is sponsored by:

European Image Information Mining Coordination Group (IIMCG), founded by:     ASI, Agenzia Spaziale Italiana - Italian Space Agency     CNES, Centre National d'Etudes Spatiales - French Space Agency     CNR, Consiglio Nazionale Delle Ricerche - Italian National Research Council     DLR, Deutsches Zentrum für Luft- und Raumfahrt - German Aerospace Center     EC-IST, European Commission - Information Society Technology     ESA-ESRIN, European Space Agency - European Space Research Institute     ETHZ, Eidgenössische Technische Hochschule Zürich - Swiss Federal Institute of Technology Zurich     EUSC, European Union Satellite Centre And extended to:     EARSC, European Association of Remote Sensing Companies

	Motivation
	Objectives
	Organisation
	Program
	Participants

Motivation

Emerging needs from big applications (e.g.: change detection, global monitoring, disaster management support, etc.) and the continuous increase in archives' size and EO sensors' variety, require new methodologies and tools for information mining and management, supported by shared knowledge. The manual process performed by experts to mine information from images is currently too complex and expensive to be applied systematically on even a small subset of the acquired scenes. This limits the full exploitation of the petabytes of archived or new data. The issue might become even more challenging in future since more missions - including constellations - are being planned, with broader sensor variety, higher data rates and increasing complexity. As an example, ENVISAT alone accumulates 400 terabytes of data every year. The problematic is common also to other domains, like medicine, multimedia, and to a broad spectrum of other sensors' data.

Results from current R&D activity might ease the access to the imagery (today mostly retrieved using spatio-temporal and a few more attributes) also through their information content. The need to access information also in large volumes of image data has stimulated the research in the field of content-based image retrieval during last decade. Many new concepts have been developed and prototyped. However the dramatic increase in volume, details, diversity and complexity, and the user demand for simultaneous access to multi-domain data urgently require new approaches for image information mining, multi-domain information management, and knowledge management and sharing (in support to information mining and training).

This year's conference focuses on securuty and intelligence thematics, for which Image Information Mining is considered of very high interest and appropriate. These thematics prove most successful when cross-cued from other intelligence disciplines, therefore the conference topics are broadened towards more generic Information Mining. In addition, because next years will be marked by an explosion of satellite imaging missions, both commercial or of restricted use, the conference is expected to bring new stimulating ideas, concepts or methods for the multiple use of the acquired image data.

The event is the fourth in the series jointly organised by ESA and EUSC (see ESA-EUSC 2005).

Objectives

Presentation should focus on Image Information Mining topics mainly for the Earth Observation domain in support to Security and Intelligence applications:

  Security and Intelligence scenarios and constraints
  Information extraction from large / complex EO image data sets
  Models, syntax and semantics for image understanding
  Information mining and knowledge discovery from heterogeneous sources
  Information and knowledge reliability
  Information and knowledge sharing
  Ontology and terminology
  Applications and use cases

The "Panel on Information Mining from images, geo-information and text" will include, depending on specific registrations, topics like:

  Use of the KIM tool (interactive information discovery from images)
  Knowledge engine for automatic classification of content from the Web
  Understanding high resolution SAR and optical images
  Automatic classification strategies
  Automatic, thematic change detection
  Image understanding supported by collateral information

Organisation

		Extensive abstract, with indication if it is for interactive presentation or poster session, via e-mail to mihai.datcu@dlr.de, copy Sergio.DElia@esa.int, (subject: IIM ESA-EUSC 2006) by July 15, 2006
		Notification or acceptance (and format for article submission) will be provided to authors by September 22, 2006
		A limited number of demonstrations can be accepted: demonstration description and resource requirements shall be provided by e-mail to l.colaiacomo@eusc.org (subject IIM ESA-EUSC 2006) within November 17, 2006
		Deadline for registration to the Conference is November 17, 2006
		Conference date: November 27-28, 2006
		Panel on Information Mining; November 29, 2006

M. Datcu, DLR

		L. Colaiacomo, EUSC
		S. D'Elia, ESA
		D. Foley, EUSC
		K. Seidel, ETHZ
		P. Kamoun, EARSC

		IIMCG members
		R.L. King, Mississippi State University - USA
		J.C. Tilton, NASA - USA
		H. Touron, EUSC
		A. Gamarra, EUSC

Program

November 27, 2006, Conference Day 1, Opening Session
"International perspectives" - Chair: L. Colaiacomo

November 27, 2006, Conference Day 1, Afternoon Session
"Theory" - Chair: A. Giros

November 27, 2006, Conference Day 1, Evening Session
"Posters" - Chair: D. Foley

November 28, 2006, Conference Day 2, Morning Session
"Applications" - Chair: K. Seidel

November 28, 2006, Conference Day 2, Afternoon Session
"Security" - Chair: S. D'Elia

November 29, 2006, Conference Day 3
"Panels" - Chair: J.L. Valero

Participants