Multi-sensor data fusion for supervised land-cover classification through a Bayesian setting coupling multivariate smooth kernel for density estimation and geostatistical techniques

The data fusion is a growing research field, which finds a natural application in the remotesensing, in particular, for performing supervised classifications by means of multi-sensor data.From the theoretical standpoint, to address such an issue, the Bayesian setting provides an elegantand consistent framework. Recently, a methodology has been successfully proposed incorporatinga geostatistical non-parametric approach for improving the estimation of the prior probabilitiesin the scope of the supervised classification. In this respect, a limitation affecting the Bayescomputation in the multi-sensor data is the naïve approach, which considers independent all thesensor measurements. Obviously, such hypothesis is unsustainable in practice, because differentsensors can provide similar information. Therefore, an enhancement of the previous describedmethod is proposed, introducing the smooth multivariate kernel method in the Bayes frameworkto furtherly improve the probability estimations. A peculiar advantage of the smooth kernelapproach concerns the fact that it is inherently non-parametric and consequently overcomes themultinormality data hypotesis. A case study is presented based on the data coming from theAQUATER project.