A novel cloud detection method based on segmentation prior and multiple features for Sentinel-2 images

Clouds in Sentinel-2 images seriously affect its usage in various fields, such as agricultural production and environmental monitoring. Although cloud masks have been provided in Sentinel-2 products, the stability of cloud detection accuracy may be affected by different types of underlying surfaces. This study presents a novel cloud detection method for Sentinel-2 images based on segmentation prior and multiple features. In the presented method, spectral, texture, and exponential features are extracted to enhance the difference between clouds and underlying surfaces. Meanwhile, segmentation results are regarded as priors to constrain pre-classification results to improve the edge accuracy of cloud detection and to obtain detection results with low false alarm rate and low omission rate. Experiments on the Sentinel-2 image dataset show that the presented method achieves good and stable cloud detection results, and the accuracy of cloud detection for six underlying surface types (impervious areas, water, croplands, bare lands, snow & ice, and forest) are above 0.93. These findings demonstrate that the presented method has the potential to effectively improve the stability of cloud detection accuracy while reducing the requirement for the number of samples.

Automated summary

This study proposes a novel cloud detection method for Sentinel-2 images based on segmentation prior and multiple features. The method extracts spectral, texture, and exponential features to enhance the difference between clouds and underlying surfaces. The segmentation results are used as priors to improve the edge accuracy of cloud detection, resulting in detection results with low false alarm rate and low omission rate. Experimental results demonstrate the effectiveness and stability of the presented method.