Effective Region Based Segmentation Technique for High Resolution Aerial Imagery

Due to tremendous progress in spatial resolution in an imagery obtained from space born platforms such as Ikonos, World-view1, IRS series, methods of segment based image analysis for generating and updating geographical information are becoming more and more important. Detailed information about the objects including their shadows is now possible to extract from remote sensing data. In this paper, we discuss the effectiveness of edge guided region growing over simple region growing segmentation technique for high resolution aerial imagery. This paper is an attempt to develop an unsupervisory algorithm for automated software to segment aerial images. Experimental results demonstrate promising performance achievements compared to other existing segmentation methods for the same. Furthermore, the simplicity of this method is an attractive feature for real-time applications.