摘要
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.
A new compressive sensing(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 recon- struct 200 bands AVIRIS hyperspectral images show that the effect of spectral sparse representation en- hances largely compared with traditional DCT dictionary and Haar wavelet dictionary, and the hyper- spectral image is reconstructed nearly perfectly at 25 % sampling rate and the spatial and spectral preci- sion is higher than existing common methods in the same condition.
出处
《红外与毫米波学报》
SCIE
EI
CAS
CSCD
北大核心
2016年第6期723-730,共8页
Journal of Infrared and Millimeter Waves
基金
国家高技术研究发展计划(863计划)(2013AA12904)
中国科学院/国家外国专家局创新国际团队(2013AA1229)~~
关键词
压缩感知
高光谱成像
稀疏表示
字典学习
重构算法
compressive sensing ( CS ), hyperspectral imaging, sparse representation, dictionary learning, reconstruction algorithm.