摘要：Many applications require remotely sensed brightness temperature (BT) data acquired with high temporal and spatial resolutions. In this regard, a viable strategy to overtake the physical limitations of space-borne sensors to achieve these data relies on fusing low temporal but high spatial resolution (HSR) data with high temporal but low spatial resolution data. The most promising methods rely on the fusion of spatially interpolated high temporal resolution data with temporally interpolated HSR data. However, the unavoidable presence of cloud masses in the acquired image sequences is often neglected, compromising the functionality and/or the effectiveness of the most of these fusion algorithms. To overcome this problem, a framework combining techniques of temporal smoothing and spatial enhancement is proposed to estimate surface BTs with high spatial and high temporal resolutions even when cloud masses corrupt the scene. Numerical results using real thermal data acquired by the SEVIRI sensor show the ability of the proposed approach to reach better performance than techniques based on either only interpolation or only spatial sharpening, even dealing with missing data due to the presence of cloud masses.
