Multi-label Cloud Segmentation Using a Deep Network
This work addresses cloud detection for meteorological or remote sensing applications, but it is incremental as it applies an existing method (U-Net) to a new task (multi-label segmentation).
The paper tackled multi-label segmentation of clouds in ground-based sky images using a U-Net deep learning architecture, achieving performance that significantly outperforms recent literature.
Different empirical models have been developed for cloud detection. There is a growing interest in using the ground-based sky/cloud images for this purpose. Several methods exist that perform binary segmentation of clouds. In this paper, we propose to use a deep learning architecture (U-Net) to perform multi-label sky/cloud image segmentation. The proposed approach outperforms recent literature by a large margin.