Morphological image filtering for improvement of textural built-up index performances in case of presence of scattered vegetation in semi-desertic areas

In this paper an improved procedure for the automatic recognition of built-up areas, using the so-called PANTEX index is presented. This index is based on analysis of image textural measures extracted using anisotropic rotation-invariant GLCM statistics. These measures may overestimate the built-up areas in case of presence of scattered vegetation having the same spatial pattern of settlements. In this paper we present a methodology able to overcome this problem. This methodology is based on an additional filtering step that pre-selects the image information to be ingested by the textural analysis phase. The test presented here uses multispectral QuickBird satellite data input at the spatial resolution of 2.4 meters. In the selected test area, with the improved procedure we estimated an overall accuracy of 88.69% in the automatic recognition of built-up areas, with an overall increase of accuracy of 20.76% respect to the basic procedure.