基于光谱稀疏模型的高光谱压缩感知重构

提出了一种基于光谱稀疏化的压缩感知采样与重构模型,通过从训练样本中构建光谱稀疏字典提升光谱稀疏化效果,同时在重构时兼顾空间图像的全变分约束进一步提升重构精度.对200波段AVIRIS高光谱场景进行压缩感知重构的实验表明,利用构建的光谱稀疏字典与传统的DCT字典和Haar小波字典相比光谱稀疏化效果明显提升,同时在25%采样下基于光谱稀疏字典几乎无差别重构出了高光谱图像,同样条件下在空间和光谱的精度与现有常用方法相比有较大的提升.

Hyperspectral compressive sensing reconstruction based on spectral sparse model

Compressive sensing imaging (CSI) has drawn wide attention due to its unique advantage that breaks through the Nyquist sampling limitation and realizes super-resolution imaging. The effect of signal sparse representation is a dominant factor of the reconstructed image quality in the CSI theory. Therefore making full use of the abundant spectral information redundancy is an effective way to improve the quality of reconstructed image for hyperspectral CSI reconstruction. A new CS sampling and reconstruction model based on spectral sparse representation is put forward in this paper. The spectral sparse dictionary is constructed from training samples to enhance the effect of sparse representation and the total variation restriction of spatial images is also considered to further enhance the precision during the reconstruction. The experiment to reconstruct 200 bands AVIRIS hyperspectral images show that the effect of spectral sparse representation enhances largely compared with traditional DCT dictionary and Haar wavelet dictionary, and the hyperspectral image is reconstructed nearly perfectly at 25% sampling rate and the spatial and spectral precision is higher than existing common methods in the same condition.