Cloud Removal in Image Time Series through Sparse Reconstruction from Random Measurements

Abstract

In this paper we propose a cloud removal algorithm for scenes within a satellite image time series based on synthetisation of the affected areas via sparse reconstruction. The high dimensionality of time series allows applying pixel-based sparse reconstruction techniques efficiently, estimating the values below a cloudy area by observing the spectral evolution in time of pixels in cloud-free areas. The process implicitly compensates the overall atmospheric interactions affecting a given image, and it is possible even if only one acquisition is available for a given period of time. The sparsifying basis is selected randomly from the time series in order to achieve a semi-automatic workflow, if the area containing clouds and their shadows is given. Favourable comparisons with the state of the art and application to supervised classification and change detection show that the proposed algorithm restores images locally contaminated by clouds and their shadows in a fast and efficient way.