An Approach for Automated Registration of Hyperspectral Images for Boresight Calibration

Parametric geocoding is a standard procedure for orthorectification of hyperspectral airborne scanner data. Boresight parameters are estimated by using the image coordinates of precisely known ground reference points. To fully automate the processing of the recorded hyperspectral data ground reference points should be selected and matched by an algorithm without user interaction. In this article a two-step procedure is presented. First, direct geocoding of the data is done without ground reference points. This step is solely based on the data of the inertial measurement unit with differential GPS. Next, the hyperspectral data is normalized and pixels are clustered with an unsupervised method. Image blocks of an edge image of the resulting regions are matched with a high resolution edge image of a digital orthophoto of the calibration site. The found correspondences are used as ground control points in the second geocoding step.