A cost-effective approach for improving the quality of soil sealing change detection from Landsat imagery

摘要

The aim of this study is to develop a cost-effective approach for soil sealing change detection integrating radiometric analysis, multi-resolution segmentation and object-based classifiers in two study areas in Italy: Campania region and Veneto region. The integrated approach uses multi-temporal satellite images and CORINE Land Cover (CLC) maps. A good overall accuracy was obtained for the soil sealing maps produced. The results show an improvement in terms of size of the minimum mapping unit and of the changed object (1,44 ha in both cases) in respect to the CLC. The approach proves to be cost-effective given the data which are provided at low or no cost and as well as the level of automation achievable.