Knowledgecentred Earth Observation KEO Final Presentation

1
Knowledge-centred Earth Observation(KEO)Final
Presentation
S. DElia, M. Iapaolo, A. Della Vecchia EOP-G
Service Support and Ground Segment Technology ESA
- ESRIN, via G. Galilei, Frascati, Italy
2
Table of Contents

• IIMCG
• KIM
• KEO
• RDSs
• ACS presentation / demo
• Systems Content
• Conclusions

3
Image Information Mining Coordination Group

• Voluntary organisation focused on
• RTD on automated / user-centred IIM(increasing
  EO data quantity / complexity)
• Cooperation
• Free information exchange
• Shared prototypes reference data sets
• Organisation of / participation to
• Conferences
• Tutorials
• IGARSS sessions
• Inspired
• IIM in Masters and PhD Programs
• CNES/DLR/ENST Competence Center

4
IIMCG - RTD Themes / Areas
Common Automation, Evolution, Massive data,
Architectures, Standards
Mobile / DSS Support Service Networks Semantics In
formation-Based Services Sensor Web Service
Discovery / Chaining GS Interface Services
Digital World Search / Actionable
Intelligence Proximity Search Distributed Data
Ident. / Access Text georeferencing Heterogeneous
Data Content Based
Mediating / Adaptive / 3D New Products Learning Se
mantics
Reference Data Sets EO Images Ground Sensors
Data Text
Pre-processing Classification, Interactive
IIM Feature, Objects, Topology Components
Chaining e-Collaboration / Grid Time
Series Distributed Processors Ident./Activation Da
ta Fusion
Components Ontology Semantics Knowledge
Discovery ImInt, GEOInt, OSInt Reasoning
Partially covered Uncovered
5
Overview of ESA Activities on IIM
Co-registration / Time Series
IIM-TS
Image Information Mining - Time Series
OrthoServ
Assessment of Ortho-Rectification services
MIR-E
Multiple Image Registration - Extension
Image Infor. Mining Services
SPA
Support by Pre-classification to Specific
Applications
CARD
Classification Application services and Reference
Datasets
KEI
KIM Extensions and Installations
PIMS-DLR
Partner Information Mining System - DLR
MIMS
MERIS Information Mining System
KEO
Knowledge-centred Earth Observation
Ontology / Terminology
OTEG
Ontology and Terminology for GMES Space Component
OTE
Ontology and Terminology for EO
SDD
Semantics driven framework for resource and
knowledge discovery
Probabilistic IM
KIMV
KIM Validation
KES
Knowledge Enabled Services
KIM
6
Table of Contents

• IIMCG
• KIM
• KEO
• RDSs
• ACS presentation / demo
• Systems Content
• Conclusions

7
Knowledge-based Information Mining (KIM)
http//kaos.esrin.esa.int/kaos

• Prototype for interactive image / collection
  analysis(for large / well characterised areas
  Features)

8
KIM Use
9
Table of Contents

• IIMCG
• KIM
• KEO
• RDSs
• ACS presentation / demo
• Systems Content
• Conclusions

10
Knowledge-centred Earth Observation
(KEO)http//keo.esrin.esa.int

• Distributed component-based programming /
  processing environment
• Create semantically identify internal /
  external Processing Components
• Create Processing Components from KIM training
  (also interactive use)
• Chain graphically Processing Components into
  Processing Chains
• Store output into Web Servers (WFS, WMS, WCS)
• Create and publish SSE services (from Processing
  Chains or output)
• Reference Data Sets
• Collections of heterogeneous data and information
  (images, documents, DEMs, GTCs, photos,
  processors, etc.)
• Support specific applications
• To grow with external contributions

11
KEO Concept
KEO
12
KEO Architecture

• Users can chain (own or system) modules and
  execute chains through the
• Dedicated client (KAOS), which activates the
• Feature Extraction Processor (FEP) engine, which
  interacts with
• FEP actuators (local or remote)

Platform-dependent modules
CLI Command Line Interface
13
KEO FEP Graphic Designer
14
Table of Contents

• IIMCG
• KIM
• KEO
• RDSs
• ACS presentation / demo
• Systems Content
• Conclusions

15
Reference Data Setshttp//geonetwork.keo.esrin.es
a.int/geonetwork
16
Search Methods (1/2)
17
Search Methods (2/2)
18
Data Visibility (1/2)
Metadata might be visible to any user
19
Data Visibility (2/2)
Metadata might be visible to any user, but
downloadable only from authorised users
20
Data Download
21
Table of Contents

• IIMCG
• KIM
• KEO
• RDSs
• ACS presentation / demo
• Systems Content
• Conclusions

22
Table of Contents

• IIMCG
• KIM
• KEO
• RDSs
• ACS presentation / demo
• Systems Content
• Conclusions

23
KIM Primitive Features
24
KIM Demonstrator
25
FEPs Calibration / Classification
Status A Available, O Ongoing, P Possible
26
FEPs Feature Extraction
Status A Available, O Ongoing, P Possible
27
FEPs Change Detection / Data Conversion
Status A Available, O Ongoing, P Possible
28
FEPs Image Processing / Segmentation
Many elementary operators (KEO)
Status A Available, O Ongoing, P Possible
29
Reference Data Sets (some provide links)

• (A)ATSR-like, Land Cover
• AATSR Test Dataset
• Baltic Sea Region database (BALANS)
• CORINE Land Cover 2000 (CLC2000)
• Global Climatologic-based Land Cover
  Classification (Ecoclimap)
• African Land Cover Database (FAO Africover)
• LANDSAT-like, Land Cover
• NOAA Coastal Change Analysis Program (C-CAP)
• Customized Worldwide RDS
• Minnesota Land Cover Classification System
• Regione Emilia Romagna
• Wisconsin Land Cover Use
• U.S. Landsat Based Land Cover Database (NLCD2001)
• SPOT-like, Land Use
• Bolzano land use database
• Customised Worldwide RDS
• Kalideos database
• Regione Lombardia land use database
• SPOT Test Dataset

• AVNIR-2, Cloud Cover
• AVNIR-2 Test Dataset
• Customised RDS
• Ice Applications
• Svartisen Glacier, Norway, Glacier Facies
  Classification, LANDSAT Imagery
• Hofsjokull Glacier, Iceland, Glacier Facies
  Classification, ERS/ENVISAT Imagery
• North coast of Newfoundland, Canada, Iceberg
  Monitoring, Ship Detection, ENVISAT Imagery
• Baltic Sea, Sea Ice Thickness Measurements,
  ENVISAT Imagery
• Others
• Classification, Landsat urban area points of
  interest
• MCI / FLH index extraction
• Planned
• Ortho-rectification (Maussane les Alpilles, Thun)
• Interferometry
• Co-registration (CNES, NCC)
• Change Detection
• Trend analysis

30
Table of Contents

• IIMCG
• KIM
• KEO
• RDSs
• ACS presentation / demo
• Systems Content
• Conclusions

31
Conclusions

• KEO provides
• Automatic extraction of key Primitive Features
• KIM collections for public test or private use
• Reference Data Sets (supporting many
  applications)
• Many Processing Components (from simple operators
  to full chains)
• KEO permits
• Automatic ingestion of images and their
  interactive exploration
• e-Cooperation for developing / validating new
  algorithms / applications
• Sharing of advanced processing components (not
  only the consolidated ones)
• Fast creation of SSE services
• KEO is relevant for
• Scientific communities (new algorithms, shared
  repository, validations, outreach)
• Eduspace (extension of capabilities, involvement
  of universities)
• Value Adders / Service Providers (quick
  implementation / test of new services)

32
Conclusions

• KEO / SSE proposed for operations within the EO
  Next Generation project
• KEO prototype improvements (for possible
  operations)
• With users
• Demonstrate the system and collect feedback /
  requirements
• Define and test operational scenarios
• Identify new FEPs
• Implement new requirements
• Implement / integrate new FEPs (from GDAL, ORFEO,
  BEAM, BEST, NEST, eduspace)
• Isolate ontology / semantics and align it to
  GSCDA
• Control visibility of and access to Processing
  Components
• Permit to run a Processing Component on a
  specific machine
• Set-up a driving User Group?

Thank you