CloudFU-Net: A Fine-Grained Segmentation Method for Ground-Based Cloud Images Based on an Improved Encoder–Decoder Structure

The segmentation of ground-based cloud image is a crucial aspect of ground-based cloud observation, with significant implications for meteorological forecasting, photovoltaic power prediction, and other related tasks. At present, the proposed method of ground-based cloud image segmentation only separates cloud from the sky background without further classifying the cloud categories. Clouds have rich fine-grained semantic features, and different types of clouds have different effects on solar irradiance, which in turn has different effects on photovoltaic power. In this article, a fine-grained segmentation method for ground-based cloud images is proposed, which is based on an improved encoder–decoder structure named CloudFU-Net. First, a ground-based cloud image fine-grained segmentation dataset for photovoltaic power prediction is constructed, and the clouds are divided into five categories with different colors under the guidance of meteorologists. Second, selective kernel (SK) is introduced in the CloudFU-Net encoder to better capture cloud of different sizes. Then, a parallel dilated convolution model (PDCM) is proposed to segment small target clouds more accurately. Finally, a content-aware reassembly of features (CARAFE) is introduced into the CloudFU-Net decoder to replace the original interpolating upsampling to better recover fine-grained semantic features. Finally, the experimental results show that the proposed CloudFU-Net has the best segmentation performance compared with other segmentation models, with Miou reaching 61.9%, which can efficiently segment different cloud genera and lay a solid foundation for accurate prediction of photovoltaic power.