Search

Clouds are the major source of clutter in optical remote sensing (RS) images. Approximately 60% of the Earth's surface is covered by clouds, with the equatorial and Tibetan Plateau regions being the most affected. Although the implementation of techniques for cloud removal can significantly improve the efficiency of remote sensing imagery, its use is severely restricted due to the poor timeliness of time-series cloud removal techniques and the distortion-prone nature of single-frame cloud removal techniques. To thoroughly remove thin clouds from remote sensing imagery, we propose the Saliency Cloud Matting Convolutional Neural Network (SCM-CNN) from an image fusion perspective. This network can automatically balance multiple loss functions, extract the cloud opacity and cloud top reflectance intensity from cloudy remote sensing images, and recover ground surface information under thin cloud cover through inverse operations. The SCM-CNN was trained on simulated samples and validated on both simulated samples and Sentinel-2 images, achieving average peak signal-to-noise ratios (PSNRs) of 30.04 and 25.32, respectively. Comparative studies demonstrate that the SCM-CNN model is more effective in performing cloud removal on individual remote sensing images, is robust, and can recover ground surface information under thin cloud cover without compromising the original image. The method proposed in this article can be widely promoted in regions with year-round cloud cover, providing data support for geological hazard, vegetation, and frozen area studies, among others. [ABSTRACT FROM AUTHOR]

Abstract: In this work, an algorithm for automatic subpixel snow mapping was developed for Moderate Resolution Imaging Spectroradiometer (MODIS) data of the Qinghai–Tibet Plateau. The algorithm consists of two parts: cloud removal and snow mapping. An approach to remove cloud was presented and it was demonstrated to remove thick and thin clouds well from MODIS images. Multiple-endmember spectral mixture analysis was used in the subpixel snow mapping of the Qinghai–Tibet Plateau, and multiple indices (including the normalized difference vegetation index and normalized difference snow index) were introduced to automatically select the endmembers. Additionally, the combined use of typical and neighboring endmembers was introduced into the unmixing of mixed pixels. Finally, highly accurate snow-cover data of the Qinghai–Tibet Plateau obtained with this algorithm were stored in a spatio-temporal database. The results of the subpixel snow mapping were validated with Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data recorded at the same time as corresponding MODIS data. According to the validation results, the correlation coefficients of the MODIS results versus the ASTER data exceed 0.9, and the root-mean-square errors are less than 0.2. [Copyright &y& Elsevier]