Scene registration in aerial image analysis

In this paper we discuss the importance of scene registration for several tasks in the automated interpretation of aerial imagery. These tasks are structure matching, stereo matching, and stereo visualization. While the processes of registration and matching have traditionally been treated as separate problems, particularly in the case of stereo matching, we describe techniques that may unify these processes. We also demonstrate the automatic generation and matching of control points in complex aerial imagery and show that the resulting registration is comparable to that achieved using manual control point selection. Finally, methods for the generation and visualization of stereo disparity images and stereo ground truth scene segmentations are described.