The effects of speckle reduction on classification of ERS SAR data

Optical Earth observation data have been used frequently in agricultural ap plications. The problem of cloud cover found with optical data can be overc ome by using radar Earth observation data, but in turn these data have a sp eckle problem. This paper describes six types of speckle reduction filter a nd assesses the capability of each to improve classification accuracy in ag ricultural applications. The best filters are Lee-Sigma, Gamma MAP ( Maximu m a Posteriori) and simulated annealing. The filters are assessed in the co ntext of identifying fields growing potatoes in the UK using Earth observat ion data, and results for other agricultural crops are also included.