Automatic Satellite Image Registration by Combination of Stereo Matching and Random Sample Consensus

In this paper, we propose a new algorithm for automated image registration or precise correction of satellite images. We assume that ground control points used previously are stored within the system. The algorithm first applies matching between the GCP chips stored and a new image to be registered and creates new control points. An automated stereo matching based on normalized cross correlation will be used for matching. Then the algorithm applies Random Sample Consensus to discriminate false matches from being considered for modeling. We believe that robust estimation scheme is important for automated image registration. We carried out experiments with SPOT images over three test sites. Through stereo matching, a number of control points were generated. The RANSAC was applied to the control points. All outliers were correctly identified for all three test sites and mapping functions estimated without outliers. The accuracy of estimation was comparable to that of estimation with control points generated all by manual measurements. The results support that our algorithm can be used for robust automated registration.