Remote Sensing Image Fusion Based on Nonnegative Dictionary Learning

For the problem of Panchromatic and multispectral remote sensing image fusion, we propose a remote sensing image fusion algorithm based on nonnegative dictionary learning. The basic idea of the algorithm is to use the panchromatic image with high spatial resolution to learn the high-low resolution dictionary pair, and to improve the fusion effect of remote sensing image by combining the nonnegativity of the image. Firstly, high resolution dictionary and low resolution dictionary are learned from high spatial resolution panchromatic image by nonnegative dictionary learning technology. Then multispectral image is sparsely represented by low resolution dictionary to obtain coefficient matrix. Finally, using coefficient matrix and high resolution dictionary, high resolution multispectral image is reconstructed. Compared with state-of-the-art methods, the proposed algorithm can get high spatial resolution and well preserve spectral information of multispectral image. Our experimental results of real QUICKBIRD and IKONOS remote sensing image fusion validate the effectiveness of the proposed algorithm.

Automated summary

The proposed algorithm utilizes panchromatic image and nonnegative dictionary learning technology to learn high and low resolution dictionary pairs, achieving remote sensing image fusion through sparse representation and reconstruction, effectively preserving spectral information of multispectral images.