Research Article Open Access

A new approach for Classifying land development in High-Resolution Remote Sensing Images

Abstract

In this paper present an unsupervised method for discovering compound image structures that are comprised of simpler primitive objects. An initial segmentation step produces image regions with homogeneous spectral content. Then, the segmentation is translated into a relational graph structure whose nodes correspond to the regions and the edges represent the relationships between these regions. Therefore, we employ two different procedures to discover the sub graphs in the constructed graph. During the first procedure the graph is discredited and a graphbased knowledge discovery algorithm is applied to find the repeating sub graphs. Even though a single sub graph does not exclusively correspond to a particular compound structure, different sub graphs constitute parts of different compound structures. We extract a large set of corners from each input image by an improved Harris corner detector. Afterward, we incorporate the extracted corners into a likelihood function to locate candidate regions in each input image. The second procedure involves graph segmentation by using normalized cuts. Since the distribution of significant relations within resulting sub graphs gives an idea about the nature of corresponding compound structure, the sub graphs are further grouped by clustering the histograms of the most significant relations.

To read the full article Download Full Article | Visit Full Article