Automatic registration of high-resolution images using local properties of features

We propose an automatic image-to-image registration of high-resolution satellite images using local properties and geometric locations of control points to improve the registration accuracy. First, coefficients of global affine transformation between images are extracted using a scale-invariant feature transform (SIFT)-based method, and features of the sensed image are transformed to the reference coordinate system using these coefficients. Then, a spatial distance and orientation difference between features of the reference and sensed images are additionally used to extract a large number of evenly distributed control points. The specified spatial distance is calculated between features of the sensed image that have been transformed to the reference coordinates and features of the reference image. Finally, the spatial distance integrated with Euclidean distances of invariant vectors is employed for local matching. The average orientation differences between control points of the two images are used for outlier elimination. A mapping function model consisting of an affine transformation and piecewise linear functions is applied to the control points for automatic registration of high-resolution images. The proposed method can extract a larger number of spatially well-distributed control points than SIFT-based methods. The registration accuracy for all sites calculated from manually selected checkpoints has acceptable geometric accuracy at the pixel level.