Gradient-Magnitude-Based Support Regions in Structural Land Use Classification

Land use classification is one of the major problems in remote sensing. Previous studies focused on multispectral information, texture-based features, and features based on edge detection to classify land usage from satellite images. In a previous study, structural features are introduced to classify land development using high-resolution satellite images. These structural features were based on line support regions (LSRs). LSRs are introduced to detect and represent straight lines in images using a pixel-grouping process. The structural features are calculated on these grouped pixels. It is shown that gradient-magnitude-based pixel grouping may also be used in structural feature calculations. Therefore, the aim of this letter is twofold. First, the previous structural feature calculation method is shown to be more general than the LSR. Second, LSR-based features are shown to require fairly high computation compared to gradient-magnitude-based features with similar classification performance