Change and Anomaly Detection
Change Detection determines area in Remote Sensing images that have essentially changed between two points in time.
Research Focus
Anomaly detection detects image regions which do not correspond to a given reference image. Change detection can be considered as a special case of anomaly detection where the reference data belongs to a previous point in time. Our research is about using multimodal data and generative AI to generate a more meaning reference to compare recent measurements with.
Publications
- Maximilian Bernhard, Niklas Strauß, Matthias Schubert: MapFormer: Boosting Change Detection by Using Pre-change Information, in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 23), 2-5 October 2023, Paris, France
- Diana Davletshina, Valentyn Melnychuk, Viet Tran, Hitansh Singla, Max Berrendorf, Evgeniy Faerman, Michael Fromm, Matthias Schubert: Unsupervised Anomaly Detection for X-Ray Images. CoRR abs/2001.10883 (2020)