Multi-temporal classification of TerraSAR-X data for wetland vegetation mapping
Résumé
This paper is concerned with vegetation wetland mapping using multi-temporal SAR imagery. Whilst wetlands play a key role in controlling flooding and nonpoint source pollution, sequestering carbon and providing an abundance of ecological services, knowledge of the flora and fauna of these environments is patchy, and understanding of their ecological functioning is still insufficient for a reliable functional assessment on areas larger than a few ha. The aim of this paper is to evaluate multitemporal TerraSAR-X imagery to map precisely the distribution of vegetation formations within wetlands, in determining seasonally flooded areas of wetlands. A series of six dual-polarization TerraSAR-X images (HH/VV) were acquired in 2012 during dry and wet seasons. Polarimetric and intensity parameters, which present a temporal variation that depends on wetland flooding status and vegetation roughness, were firstly extracted. The parameters were then classified based on Support Vector Machines (SVM) techniques using a specific kernel adapted to the comparison of time-series data. The results show that the Shannon entropy parameter allows discriminating vegetation formations within wetland with more accuracy than intensity parameters.