PROJECT TITLE :

A New European Settlement Map From Optical Remotely Sensed Data

ABSTRACT:

An application of a general methodology for processing terribly high-resolution imagery to produce a European Settlement Map (ESM) in support of policy-makers is presented. The process mapped around 10 million $textkm^2$ of the European continent. The input image data are satellite SPOT-five/6 pan-sharpened multispectral images of two.5- and 1.5-m spatial resolution, respectively. This is often the primary time that remote sensing technology demonstrates capability to produce a continental info layer using a pair of.5-m input pictures. Moreover, it's the very best resolution continental map produced so so much. The presented workflow is data-driven and consists in fully automatic image Information Extraction primarily based on textural and morphological image analysis. The learning methodology allows the processing of high-resolution image knowledge using coarse resolution thematic layers as reference. Validation shows an overall accuracy of 96percent with omission and commission errors less than four% and one%, respectively.