Elimination of False Detections by Mathematical Morphology for a Semi-automatic Buildings Extraction of Multi Spectral Urban Very High Resolution IKONOS Images

Elimination of False Detections by Mathematical Morphology for a Semi-automatic Buildings Extraction of Multi Spectral Urban Very High Resolution IKONOS Images Journal of Intelligent Computing A. Benali, H. DermÃ¨che2, E. Zigh1 5 3 2014 http://www.dline.info/jic/fulltext/v5n3/1.pdf We propose in this paper a method based on mathematical morphology for building extraction in a very high spatial resolution satellite urban areas images, it requires no exogenous variable, unlike other approaches (e.g., using elevation data or supervised classification post processing [1]). It consists on using several morphological operations such as hit-or-miss transform (HMT), the geodesic reconstruction and smoothing. Comparative studies of two methods (including that of [1]) are presented showing the interest of the approach we used.