Multiscale Attention Feature Aggregation Network for Cloud and Cloud Shadow Segmentation

Cloud and cloud shadow segmentation is one of the most important problems in remote sensing image processing. Due to the vulnerability to ground object interference, noise interference and other factors, and the lack of generalization ability, traditional deep learning networks would inevitably lose details and spatial information, resulting in imprecise segmentation of cloud and cloud shadow boundaries, missing detection, and false detection. In order to solve these problems, a multiscale attention feature aggregation network is proposed, which extracts semantic information at different levels based on the residual network. A multiscale strip pooling attention module is designed to extract multiscale context information and deep spatial channel information. In order to improve the feature extraction of the model, the deep multihead feedforward transfer attention module is introduced to enable the adjacent two layers of the backbone network to guide each other for feature mining. Then, a bilateral feature fusion module is used to guide the fusion of low-level semantic information and high-level detail information. Finally, in order to enhance the repair of boundary details of cloud and cloud shadow, a boundary refinement boosting model is designed. The experimental results show that our model can handle complex cloud cover scenes and has excellent performance on the cloud, the cloud shadow dataset, and the cloud and snow dataset based on WorldView2 (CSWV) dataset. Its segmentation accuracy is superior to the existing methods, which is of great significance to the related work of cloud detection.