PROJECT TITLE :

Accurate Detection of Anthropogenic Settlements in Hyperspectral Images by Higher Order Nonlinear Unmixing

ABSTRACT:

In order to realize a higher data of the impact of the anthropogenic extents over the setting, extracting reliable and effective information by Earth observations (EOs) is crucial to help developing a sound human–surroundings interaction (HEI) assessment. During this sense, the employment of future hyperspectral sensors for wide space characterization ends up in the need of hyperspectral unmixing (HSU) architectures to recognize urban materials and structures. Additional, as urban settlements are typically characterised by geometrically and spectrally advanced situations, the nonlinear reflectance interplay among the elements that represent each scene should be terribly well detailed and described therefore that a thorough data of the scenes can be allotted. During this paper, properly set higher order nonlinear mixture models are used to perform an correct characterization of the anthropogenic settlements in many EO scenes acquired in numerous continents. Moreover, a complete new index for estimation of urban extents is provided. Experimental results show how the proposed approach is in a position to deliver accurate and reliable characterization of urban materials and extents.