NL FR EN
www.belgium.be

A classification framework for habitat status reporting with remote sensing methods (HABISTAT)

Projet de recherche SR/00/103 (Action de recherche SR)

Personnes :

  • Dr.  KEMPENEERS Pieter - Vlaamse Instelling voor Technologisch Onderzoek (VITO)
    Coordinateur du projet
    Partenaire financé belge
    Durée: 1/12/2006-31/12/2010
  • Dr.  PAELINCKX Désiré - Instituut voor Natuur- en Bosonderzoek (INATBOS)
    Partenaire financé belge
    Durée: 1/12/2006-31/12/2010
  • Prof. dr.  SCHEUNDERS Paul - Universiteit Antwerpen (UA)
    Partenaire financé belge
    Durée: 1/12/2006-31/12/2010
  • Prof. dr.  CANTERS Frank - Vrije Universiteit Brussel (VUB)
    Partenaire financé belge
    Durée: 1/12/2006-31/12/2010
  • Dr.  MUCHER Sander - Centrum Geo-Informatie (CENGEO)
    Partenaire financé étranger
    Durée: 1/12/2006-31/12/2010

Description :

Context and objectives

Timely and accurate habitat reportage is vital to monitoring the biodiversity and ecological quality of our environment. Remote sensing methods can be utilized to this end but existing data and classification methods fall short of the purposes of habitat reportage in several aspects:

- Airborne hyperspectral data are suitable but coverage is inadequate
- Existing methods have not addressed the issue of habitat structure which are most important for assessing habitat quality
- Most existing remote sensing methodologies have not been tested vigorously for operational purposes.
The objective of this project is to provide a tool that allows better status reporting on habitats using remote sensing data. For this, an enhanced state-of-the-art classification framework will be designed and modelling techniques will be used.


Methodology

• Three study areas will be covered by satellite data, airborne hyperspectral data: Kalmthoutse heide, Dijle valley an d Veluwe (NL). The areas contain relevant habitat types and well studied by the partners in the past. During this project, new field work will be performed. This will provide new reference data, required for training and validating the classification framework.
• Both spectral and (spatial) contextual information will be combined. In addition, ensemble classifiers will increase the accuracy of the vegetation maps. Image enhancement techniques (superresolution) will be applied to increase the applicability of remote sensing data for habitat status reporting. The vegetation condition will also be assessed using model inversion.

Results expected

- 6 peer reviewed journal papers
- Classification framework for habistat status reporting
- Integrated processing chain for SR image reconstruction including classification framework
- International Work shops

Documentation :