Potential of Using Automatically Extracted Straight Lines in Rectifying High Resolution Satellite Images

The quick advance in remote sensing technologies provides the ability to acquire high quality metric information. This is achievable by forming the relationship between image coordinates and ground coordinates as 2D and 2D-to3D transformation models. Most of these models are based on point features. Although point-based transformation models are well developed, it is time-consuming and costly to measure point coordinates manually. In addition, automatic point extraction algorithms especially in satellite images are far inferior in quality. This makes other feature-based transformation models more attractive. Linear features have greater potential than other features not only in automation but also in representation and modelling. This study investigates rectifying satellite images with different resolutions and orientations using line-based transformation models. In addition, the relative relationships between linear features are imposed by incorporating geometric constraints. Straight lines are extracted using an automated linear feature extraction algorithm. Experiments are conducted with different sets of straight lines and their results are reported and analyzed. The research reveals that line-based transformation models provide equivalent results to those obtained using point-based transformation models especially when geometric constraints are forced. In addition, combined point/line-based transformation models were also investigated and the results are similar to those achieved with point or line features only.