Abstract/Summary

The coexistence of cloud and snow is very common in remote sensing images. It presents persistent challenges for automated interpretation systems, primarily due to their highly similar visible light spectral characteristic in optical remote sensing images. This intrinsic spectral ambiguity significantly impedes accurate cloud and snow segmentation tasks, particularly in delineating fine boundary features between cloud and snow regions. Much research on cloud and snow segmentation based on deep learning models has been conducted, but there are still deficiencies in the extraction of fine boundaries between cloud and snow regions. In addition, existing segmentation models often misjudge the body of clouds and snow with similar features. This work proposes a Multi-scale Feature Mixed Attention Network (MFMANet). The framework integrates three key components: (1) a Multi-scale Pooling Feature Perception Module to capture multi-level structural features, (2) a Bilateral Feature Mixed Attention Module that enhances boundary detection through spatial-channel attention, and (3) a Multi-scale Feature Convolution Fusion Module to reduce edge blurring. We opted to test the model using a high-resolution cloud and snow dataset based on WorldView2 (CSWV). This dataset contains high-resolution images of cloud and snow, which can meet the training and testing requirements of cloud and snow segmentation tasks. Based on this dataset, we compare MFMANet with other classical deep learning segmentation algorithms. The experimental results show that the MFMANet network has better segmentation accuracy and robustness. Specifically, the average MIoU of the MFMANet network is 89.17%, and the accuracy is about 0.9% higher than CSDNet and about 0.7% higher than UNet. Further verification on the HRC_WHU dataset shows that the MIoU of the proposed model can reach 91.03%, and the performance is also superior to other compared segmentation methods.