Spatiotemporal reflectance fusion based on location regularized sparse representation

Spatiotemporal reflectance fusion plays an important role in providing earth observation with both high-spatial and high-temporal resolutions, and sparse representation is one of the popular strategies to implement spatiotemporal fusion. However, the existing methods generally suffers from instability of sparse representation for the fine and coarse image pairs. In this paper, we demonstrate that such instability can be addressed by exploiting spatial correlations among the neighboring fine images, which is mathematically formulated as a location regularized term. A fast iterative shrinkage-thresholding algorithm (FISTA) is then employed to find the optimal solution. Experimental results show that the performance of proposed method outperforms other relevant state-of-the-art fusion approaches.