基于光谱稀疏模型的高光谱压缩感知重构
投稿时间:2016-05-24  最后修改时间:2016-09-30  点此下载全文
引用本文:汪琪,马灵玲,唐伶俐,李传荣,周勇胜.基于光谱稀疏模型的高光谱压缩感知重构[J].红外与毫米波学报,2016,35(6):723~730].WANG Qi,MA Ling-Ling,TANG Ling-Li,LI Chuan-Rong,ZHOU Yong-Sheng.Hyperspectral compressive sensing reconstruction based on spectral sparse model[J].J.Infrared Millim.Waves,2016,35(6):723~730.]
摘要点击次数: 160
全文下载次数: 198
作者单位E-mail
汪琪 中国科学院光电研究院 定量遥感信息重点实验室 wangqi@aoe.ac.cn 
马灵玲 中国科学院光电研究院 llma@aoe.ac.cn 
唐伶俐 中国科学院光电研究院  
李传荣 中国科学院光电研究院  
周勇胜 中国科学院光电研究院  
基金项目:国家高技术研究发展计划(863计划)(No. 2013AA121304);中国科学院/国家外国专家局创新国际团队(No. 2013AA1229)
中文摘要: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.
中文关键词:压缩感知  高光谱成像  稀疏表示  字典学习  重构算法
 
Hyperspectral compressive sensing reconstruction based on spectral sparse model
Abstract: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 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.
keywords:compressive sensing(CS), hyperspectral imaging, sparse representation, dictionary learning, reconstruction algorithm
查看全文  查看/发表评论  下载PDF阅读器

版权所有:《红外与毫米波学报》编辑部