Abstract: A robust building detection methodology is proposed in this paper unlike classical classification methods, where self supervision data can be automatically extracted from the image by using shadow and its direction as an invariant for building object. In this methodology; first the vegetation regions are detected from a given satellite image and local directional fuzzy landscapes representing the existence of building are generated from the shadow regions using the direction of illumination obtained from image metadata. For each landscape, foreground (building) and background pixels are automatically determined and a bi partitioning is obtained using a graph-based algorithm, Grabcut, which is further modified by an iterative bio inspired optimization: Firfly Algorithm. This work towards the optimization k-means clustering used in grab cut method.

Keywords: Geographical Information System (GIS), Normalised Infra red (NIR) band, firefly algorithm.