University of Twente Proceedings

Login

Towards a typology of land-cover/land-use evolutions using high resolution satellite image time series: application to the metropolitan area of Strasbourg (France)

Share/Save/Bookmark

Guttler, F.N. and Puissant, A. and Gancarski, P. (2016) Towards a typology of land-cover/land-use evolutions using high resolution satellite image time series: application to the metropolitan area of Strasbourg (France). In: GEOBIA 2016 : Solutions and Synergies., 14 September 2016 - 16 September 2016, University of Twente Faculty of Geo-Information and Earth Observation (ITC) .

[img]
Preview
PDF
815kB
Event: GEOBIA 2016 : Solutions and Synergies., 14 September 2016 - 16 September 2016, University of Twente Faculty of Geo-Information and Earth Observation (ITC)
Abstract:In this work, we propose an original approach to extract structured information from long-term satellite image time series (SITS) which can be employed to construct a typology of land-cover/land-use (LCLU) evolutions. Through a semi-supervised framework we combine per-pixel and object-based image analysis with data mining techniques. Our experiments are applied to the metropolitan area of Strasbourg (France) using nine high spatial resolution (20 m) SPOT images acquired between 1992 and 2011. The framework is organized in four main steps: (a) construction of image objects, (b) multi-strategy fuzzy learning approach to predict LCLU class membership at pixel level, (c) generation of structured information at object level and (d) mining structured information across the time-series.
Item Type:Conference or Workshop Item (Paper)
Link to this item:https://doi.org/10.3990/2.391
Conference URL:https://www.geobia2016.com/
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page