Developing a generic framework for library based multi-site mapping of urban areas.

The main aim of this project is to propose a conceptual framework for the development and use of a generic urban library (GUL). This entails the definition of a suitable data model and metadata scheme for archiving urban image spectra, as well as the definition of a set of tools for the dynamic use of the library, including tools for extracting endmember spectra from available imagery, for automatic labelling of these spectra and storage in the GUL, as well as tools for resampling/ transforming library spectra and for selecting optimal spectra from the library for user-specific applications. A GUL management tool will be developed that can be made accessible to the user’s community. Proof-of-concept of the tool will be delivered through a series of experiments aimed at testing the use of the tool for multi-site/multi-source urban mapping, both at high as well as medium spatial/spectral resolution. The hypothesis of the research is that a generic urban library (GUL) containing multi-site, multi-source image spectra may provide the ground for the transferability of urban mapping approaches at different spatial/spectral scales and thus contribute to the development of automated workflows for urban mapping applications.

Belgian Science Policy