Image-based change detection with deep neural networks for satellite inspection

Kurzfassung

This internship report deals with the topic of change detection in the context of in-orbit satellite inspection. In the imagined scenario, images are taken of a known, possibly damaged target satellite, which are then compared offline on the ground with a reference data set with the aim of identifying geometric changes. The main focus of the work is the investigation of the use of state-of-the-art CNNs for the mentioned task.