Land cover classification by using multi-temporal COSMO-SkyMed data

Abstract

The objective of this paper is to report on the crop classification activities carried out during the first year of the Italian project “Use of COSMO-SkyMed data for LANDcover classification and surface parameters retrieval over agricultural sites” (COSMOLAND), funded by the Italian Space Agency. The project intends to contribute to the COSMO-SkyMed mission objectives in the agriculture and hydrology application domains. In particular, the objective of the classification activities is to assess the potential of multi-temporal series of X-band COSMO-SkyMed SAR data for crop classification. The selected agricultural site is located in the Capitanata plain close to the Foggia town (Puglia region, Southern Italy). Over this area, 8 Stripmap PingPong COSMO Sky-Med images at HH/HV polarization and at low incidence angle were acquired from April to August 2010. In the paper, a classification scheme based on the Maximum Likelihood algorithm is applied to the multi-temporal data set and its accuracy is assessed with respect to a reference map obtained by means of SPOT data.