| Bibtype | Inproceedings |
|---|---|
| Bibkey | Fischer/etal/2020b |
| Author | Fischer, Raphael and Piatkowski, Nico and Pelletier, Charlotte and Webb, Geoffrey and Petitjean, Francois and Morik, Katharina |
| Ls8autor |
Fischer, Raphael
Morik, Katharina Piatkowski, Nico |
| Editor | Webb, Geoffrey and Cao, Longbing and Zhang, Zhongfei and Tseng, Vincent S. and Williams, Graham and Vlachos, Michalis |
| Title | No Cloud on the Horizon: Probabilistic Gap Filling in Satellite Image Series |
| Booktitle | Proceedings of the {IEEE} 7th International Conference on Data Science and Advanced Analytics ({DSAA}) |
| Series | Environmental and Geo-spatial Data Analytics |
| Pages | 546--555 |
| Publisher | The Institute of Electrical and Electronics Engineers, Inc. ({IEEE}) |
| Abstract | Spatio-temporal data sets such as satellite image series are of utmost importance for understanding global developments like climate change or urbanization. However, incompleteness of data can greatly impact usability and knowledge discovery. In fact, there are many cases where not a single data point in the set is fully observed. For filling gaps, we introduce a novel approach that utilizes Markov random fields (MRFs). We extend the probabilistic framework to also consider empirical prior information, which allows to train even on highly incomplete data. Moreover, we devise a way to make discrete MRFs predict continuous values via state superposition. Experiments on real-world remote sensing imagery suffering from cloud cover show that the proposed approach outperforms state-of-the-art gap filling techniques. |
| Month | 10 |
| Year | 2020 |
| Projekt | ML2R |
| Url | https://ieeexplore.ieee.org/document/9260084 |
|---|