Building detection from aerial images using Hough transform and intensity information

Abstract

Detection of buildings is a significant branch of the automated aerial image interpretation problem. Automatic detection of buildings enables construction of maps, detecting changes, and monitoring urbanization. Due to the complexity and uncontrolled appearance of the scene, an intelligent fusion of different methods gives better results. To solve this problem different methods have been proposed but each of them has some shortcomings and as a consequence does not work properly in all geographical regions. In this paper, a novel semiautomatic approach for building detection using Hough transform and intensity information is presented. This method benefits from segmentation of aerial images using great tools. This segmentation will be able to estimate the centres' location of building in an image independent of geographical region's properties. Besides, it uses the Hough transform for verifying the appearance of building in estimated centres. Experimental results show the positive abilities of proposed method.