6533b837fe1ef96bd12a2fe7
RESEARCH PRODUCT
Convolutional Long Short-Term Memory Network for Multitemporal Cloud Detection Over Landmarks
Adrian Perez-suayJose E. AdsuaraLuis Gómez-chovaGonzalo Mateo-garciasubject
business.industryComputer scienceDeep learning0211 other engineering and technologiesCloud detectionPattern recognition02 engineering and technology010501 environmental sciences01 natural sciencesConvolutional neural networkImage (mathematics)Support vector machineLong short term memoryArtificial intelligenceLayer (object-oriented design)business021101 geological & geomatics engineering0105 earth and related environmental sciencesdescription
In this work, we propose to exploit both the temporal and spatial correlations in Earth observation satellite images through deep learning methods. In particular, the combination of a U-Net convolutional neural network together with a convolutional long short-term memory (LSTM) layer is proposed. This model is applied for cloud detection on MSG/SEVIRI image time series over selected landmarks. Implementation details are provided and our proposal is compared against a standard SVM and a U-Net without the convolutional LSTM layer but including temporal information too. Experimental results show that this combination of networks exploits both the spatial and temporal dependence and provides state-of-the-art classification results on this dataset.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2019-07-01 | IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium |