Project Title   KEO Demonstrator with Models for Land Use Management
Project Acronym   KLAUS
Contractor(s)   EOX, ACS, DLR, SISTEMA, ENVEO, CNES, Epistematica


Image Context
       How it will Work



A long-term ESA aim has been the implementation of Image Information Mining (IIM) techniques for improving high performance analysis processing and for dealing with huge amounts of Earth Observation satellite data. These efforts led during years to design the Knowledge-centred Earth Observation (KEO) prototype system, a modular and scalable Component-based Processing Environment (CPE) which permits to:

  Image Ease the access to EO data and relevant information extracted from them
  Image Provide a large set of tools for EO data processing (bridging the gap between Data and Information)
  Image Expand the use of EO data by supporting and automating the identification and extraction of information relevant for users
  Image Encourage the use of a common scientific cooperative environment

The KEO prototype permits users to interactively extract relevant features and information from EO data, either through a generic probabilistic technique (KIM subsystem) or by means of specific processing algorithms (FEP subsystem), and to provide outputs, i.e. valuable information extracted from data, in easily accessible formats.

The Orfeo Tool Box (OTB - see http://www.orfeo-toolbox.org/otb/) is an open source C++ library developed by CNES, providing a huge number of image processing functionalities which can be used for developing complex image processing applications optimized for EO data. OTB classes are in principle suited also to be integrated into KEO which would offer a substantial enrichment of the KEO prototype functionality.

During last years ESA funded a series of projects in the field:

  Image Knowledge-based Information Mining (KIM)
  Image Knowledge-centred Earth Observation (KEO)
  Image Image Information Mining on Time Series (IIM-TS)
  Image KEO Extensions and Installations (KEI)
  Image Classification Application-services and References Datasets (CARD)
  Image Support by Pre-classification to specific Applications (SPA)
  Image Assessment of European Ortho-rectification and Co-registration Services (OrthoServ)
  Image Open Access Ontology / Terminology for the GMES Space Component (OTEG)
  Image Service Support Environment (SSE)

Along the trail blazed by these projects, requirements and expertise have been collected also with regards to various end-user applications. Specifically in the application domains of vegetation management, hydrological hazards management, fire and burnt areas management, as well as solar irradiance monitoring specific interest for testing and validating services based on KEO technology could be determined. It could also be observed that a growing number of European organizations such as the European Satellite Centre (EUSC) and the European Maritime Safety Agency (EMSA) are interested to qualify KEO and related service approaches for potential operational deployment.



Given the above background, ESA decided to launch the KLAUS project in order to specifically encompass the following activities:

  Image Upgrading of the KEO prototype into a demonstrator, including improvements, availability, reliability and performance
  Image Assessment of the potentialities of the KEO demonstrator with selected Key Users for specific KEO Demonstrator Applications (KDA) in land use management, addressing also issues related to:
  • Generalised data models

  • Bidirectional interfaces with user’s systems

  • Implementation of new Processing Components in CPE

  Image Definition of possible KIM enhancements
  Image Enhancements of EO image co-registration chains and of inter-equalization tools for Satellite Image Time Series (SITS)
  Image Integration of part of the CNES Orfeo Tool Box as KEO processing components
  Image Support/organization of wider stakeholder group (including EUSC and EMSA) for discussion/agreement of operational scenarios
  Image Identification of possible KEO operational configurations and related transfer to operations requirements



The KEO architecture (shown in Figure 1) includes:

  Image The Knowledge-based Information Mining (KIM) subsystem with enhanced functions
  Image The Component-based Processing Environment (CPE) for distributed processing and graphic programming for automated extraction of information from EO images
  Image The user interface client, named KEO Application Operating on Services (KAOS), to access KIM and the CPE


Figure 1

Processing Components can be either Software Modules or Feature Extraction Processors (FEPs). The Software Modules, deployed either on centralised KEO machines (i.e. at ESRIN premises) or on remote machines (e.g. partners’ premises), can be:

  Image Written in JAVA
  Image Written in any other programming language but wrapped by a Command Line Interface (CLI)
  Image Provided as Web Services (WS)

The Software Modules are executed within the CPE only if embedded into FEPs. A FEP can include one or more Software Modules or combinations of other FEPs. The CPE core is a FEP Engine (see Figure 2), which activates FEPs via centralised or remote FEP Actuators according to the way in which they were chained using KAOS.


Figure 2

More details can be found in the KAOS User Manual.

A KEO Tutorial is also available for users in order to ease their access and use of system functionalities.


For development support, testing and validating of KEO, a Reference Data Sets infrastructure (RDS), managed within an GeoNetwork catalogue and accessible via standard browsers, is maintained by ESA. RDS contains collections of heterogeneous material (images, text, photos, digital elevation models, etc.) for specific topics or geographic areas.


How it will Work

Under the KLAUS project (started at the end of 2009), different tasks are planned to be carried out. The first set of addressed issues focus on the upgrade of KEO with respect to:

  Image Installation package enhancement
  Image Graphical user environment performance improvements
  Image User management functions
  Image FEP execution management
  Image System monitoring
  Image FEP/CLI import/export improvements
  Image Extension of semantic search features
  Image Improvement of overall KEO operability
  Image Enhancements of the Components-based Programming Environment

A next set of KLAUS activities relates to improvements of the multi-temporal registration and equalization processing chains (previously demonstrated) and to the implementation of a further number of Processing Components into KEO.

In order to demonstrate the KEO environment to users, a set of applications (named KDAs) will be implemented focused on the following topics:

  Image Applications for biomass estimation
  Image Applications for hydrological hazards management
  Image Applications for fires and burned areas management
  Image Application for solar irradiance monitoring

For system requirements definition and systems validation a number of Key Users (KU) are involved. At present, the identified KUs are:

  Image Parco Nazionale dei Monti Sibillini (PNMS), Italy
  Image Unione Nazionale Comuni Comunità Enti Montani (UNCEM), Italy

All developed applications in KLAUS deliver output products directly usable by the KU for their decision making process.

In addition a widening-up to a larger representation of users communities (EMSA, EUSC, etc.) is organized via a user consultation process in order to assert representative requirement, expectations and suggestions as orientation lines for future KIM and KEO developments. Possible KEO operational configurations are identified and related Transfer To Operations schemes from these operational scenarios and from results of a ranking of most promising KIM and KEO implementations are defined.



In accordance with ESA intentions and requirements, the project will produce technical and managerial deliverables associated with the following top-level Work Packages (for further details see the above “How it works??? section):

  Image KEO Demonstrator Implementation
  Image KEO Demonstration for Land Use Management
  Image KIM / KEO Enhancements
  Image Co-registration Enhancement
  Image Operational Scenarios and Configurations


Contributors to this page: andreadv .

Page last modified on Tuesday 14 of December 2010 11:19:19 CET by andreadv.