Bandelet transformation based image registration

Abstract

Perfect image registration is an unsolved challenge that has been attempted in a multitude of different ways. This paper presents an approach for single-modal, multi-view registration of aerial imagery data that uses bandelets in the preprocessing phase to extract key geometric features and limit the amount of details in the image that must be considered during the feature matching process. Applying the bandelet decomposition on both the reference and target images before feature extraction will limit the control point selection process to only those points with the most relevant geometric data. The approach uses a multi-scale approach to estimate a transformation that converges to an optimal solution as well as reduce the computation time for real-time image registration. The bandelet basis also provides for a more effective feature (e.g. corner) detection and extraction method because it determines the geometric flow and allows for shifted patches in the orthogonal direction of the geometric flow. Theoretically the bandelet results in less false positives and better detection rates than existing methods. The Bandelet-based Image Registration (BIR) method has applications in image fusion, change detection, object recognition, autonomous navigation, and target tracking.