Datcu

Information Mining for SSEMihai Datcu (DLR Oberpfaffenhofen) Andrea Colapicchioni (ACS Rome) Klaus Seidel (ETH Zurich): 

Information Mining for SSE Mihai Datcu (DLR Oberpfaffenhofen) Andrea Colapicchioni (ACS Rome) Klaus Seidel (ETH Zurich)

Information Mining for SSEIIM for TerraSA-X payload ground segmentIIM for MERIS archivesIIM for users of EO data: 

Information Mining for SSE IIM for TerraSA-X payload ground segment IIM for MERIS archives IIM for users of EO data

Slide3: 

25m ERS 10m Radarsat 2m Pol E-SAR 0.5m Aerosensing Motivations

Slide4: 

perspective view Where is the information? SRTM/X-SAR DEM 30m AEROSENSING Buildings 0.5m

E-SAR Dresden exploration of image content : 

E-SAR Dresden exploration of image content

Scene elements structure: bridge: 

Scene elements structure: bridge

Building reconstruction: 

Building reconstruction

Summary: 

Summary

Slide9: 

Image time series: time scales t(day) % pixels 0 Car,Plane apparition Snow, Rain Clouds 100 1 Factory smoke Ice, Wind effects 10 365 Crop evolutions Seasonal effects Building

IMAGE INFORMATION MINING PROJECTS in ESA TRP: 

SUMMARY KIM - Knowledge driven Information Mining in remote sensing image archives 2001-2002: DLR, ETH Zurich, ACS Rome, NERSC Bergen KES - EO domain specific Knowledge Enabled Services 2002-2004: ACS Rome, DLR, ETH Zurich KIMV - KIM Validation for EO archived data exploitation support 2003-2004: ACS Rome, DLR, ETH Zurich KEO - Knowledge-centric Earth Observation 2004-2006: ACS Rome, DLR, ETH Zurich,… IMAGE INFORMATION MINING PROJECTS in ESA TRP

KIM - Knowledge driven Information Mining in remote sensing image archives: 

Objectives: create a prototype system of a next generation architecture to help the users to gather relevant information rapidly, manage and add value to the huge amounts of historical and newly acquired satellite data-sets Data: ERS, Landsat, Ikonos, (data volume ~50 scenes) Evaluators and users: ESRIN, EUSC, NERSC, DLR Output: prototype system KIM - Knowledge driven Information Mining in remote sensing image archives

KES - EO domain specific Knowledge Enabled Services : 

KES - EO domain specific Knowledge Enabled Services Objectives: design and demonstrate a scalable prototype applicable to a number of fields supporting image information mining and other related user interactions, knowledge acquisition and sharing within user communities, multi - type data handling (image, text, GIS), up to semantic interactions and knowledge communication Data: ERS, Landsat, HR SAR and optical (data volume ~200 scenes) Evaluators and users: ESRIN, EUSC, DLR Output: prototype system River Domain Ontology Semantics Labels Features Images

KIMV - KIM Validation for EO archived data exploitation support: 

KIMV - KIM Validation for EO archived data exploitation support Objectives: to implement, test and evaluate a quasi-operational environment for simple access also as MASS Services to enhanced image selection functions (image selection by combinations of standard spatio – temporal - parameters and image information content queries) Data: MERIS, ERS, Landsat, SPOT… (data volume ~5 000 scenes) Evaluators and users: ESRIN, EUSC, CNES, DLR, universities, industry (total ~15 users) Output: pre-operational system

KEO - Knowledge-centric Earth Observation : 

KEO - Knowledge-centric Earth Observation Objectives: a prototype system and environment to foster the enlargement of EO data utilisation, and in particular of the large archives of multi-mission and multi-temporal images, provide a better support to research, value-adding industry, service providers and EO user communities, like scientific investigations, risk and disaster management, or in the GMES programme Data: TerraSAR, ENVISAT, ERS, Landsat, SPOT… (data volume ~100GB/day….) Evaluators and users: ESRIN, DLR, EUSC, CNES, universities, industry. Output: operational system

KEO Architecture: 

KEO Architecture

Slide16: 

Proposed Architecture TerraSAR-X Payload GS

Slide17: 

http://isis.dlr.de/mining/

Data-Information-Knowledge: 

Data-Information-Knowledge -applicable to a number of fields -knowledge acquisition and sharing within user communities -multi - type data handling -knowledge communication River Domain Ontology Semantics Labels Features Images

SSE including KIM and DIMS (TerraSAR GS): 

SSE including KIM and DIMS (TerraSAR GS)

Information mining for SSE: 

Information mining for SSE Data Information Knowledge Understanding Data management Data mining Information mining &KDD Data & Scene understanding

Slide21: 

Data Information Knowledge Understanding Data management Data mining Information mining &KDD Data & Scene understanding SENSORS USERS

ADVANCED COMMUNICATION CONCEPT: 

ADVANCED COMMUNICATION CONCEPT

The European Image Information Mining Coordination Group IIMCG: 

Members: ASI, CNES, CNR, DLR, EC-IST, ESA, ETHZ, EUSC Chair: Sergio D‘Elia, ESA/ESRIN IIMCG focus: research and technological activities for automated and user centred extraction of information from EO images and image archives in support to content understanding Events: ESA-EUSC 2002: Joint seminar on Knowledge driven Information Management in Earth Observation data, ESRIN, Frascati, December 5-6, 2002, Madrid, March 17-18, 2004 ESA-EUSC 2005: Theory and Applications of Knowledge driven Image Information Mining with focus on Earth Observation, ESRIN, Frascati,October, 2005 The European Image Information Mining Coordination Group IIMCG