基于稀疏张量分解的高光谱图像压缩
|
摘要
针对高光谱图像带来的大量数据存储和传输的问题,本文提出了一种基于稀疏张量分解的高光谱图像压缩方法。首先,将高光谱图像作为三阶张量进行分析。其次,通过核心张量和压缩比的关系进行张量分解。最后,对数据进行稀疏编码处理。实验结果证明本文方法相对于现有方法来说,重构图像可以获得更高的信噪比,压缩时间更短,具有更好的压缩效果。
Aiming at the problem of large amount of data storage and transmission caused by hyperspectral images, a method of hyperspectral image compression based on sparse tensor decomposition is proposed in this paper. Firstly, hyperspectral images are analyzed as third-order tensors. Secondly, tensor decomposition is carried out through the relation between core tensor and compression ratio. Finally, sparse coding is performed for the data. Experimental results show that compared with the existing methods, the proposed method can achieve higher SNR, shorter compression time and better compression effect.
Aiming at the problem of large amount of data storage and transmission caused by hyperspectral images, a method of hyperspectral image compression based on sparse tensor decomposition is proposed in this paper. Firstly, hyperspectral images are analyzed as third-order tensors. Secondly, tensor decomposition is carried out through the relation between core tensor and compression ratio. Finally, sparse coding is performed for the data. Experimental results show that compared with the existing methods, the proposed method can achieve higher SNR, shorter compression time and better compression effect.
引文
[1]孙玉宝,李欢,吴敏,吴泽彬,贺金平,刘青山,基于图稀疏正则化多测量向量模型的高光谱压缩感知重建[J],电子与信息学报,2014,36(12):2942-2948.
[2]王忠美,杨晓梅,顾行发.张量组稀疏表示的高光谱图像去噪算法[J],测绘学报,2017,46(5):614-622.DOI:10.11947/j.AGCS.2017.20150403.WANG Zhongmei,YANG Xiaomei,GU Xingfa.Hyperspectral Image Denoising Based on Tensor Group Sparse Representation[J].Acta Geodaetica et Cartographica Sinica,2017,46(5):614-622.DOI:10.11947/j.AGCS.2017.20150403.
[3]刘亚楠,涂铮铮,罗斌,基于反馈稀疏约束的非负张量分解算法[J],计算机应用,2013,33(10):2871-2873.
[4]万晨坤,王斌,基于切片映射张量分析的高光谱图像压缩[J].自然科学,2015,54(6):696-705.
[5]王磊,王斌,张立明,基于张量分析和小波包变换的高光谱图像压缩[J].自然科学,2013,52(3):371-379.
[6]Tamara G.Kolda,Brett W.Bader,Tensor Decompositions and Applications.2009 Society for Industrial and Applied Mathematics.SIAM REVIEW,2009,51(3),pp.455-500.
[7]吴倩,张荣,徐大卫,基于稀疏表示的高光谱数据压缩算法[J].电子与信息学报,2015,37(1),78-84.
[8]Liu Fang,Wu Jiao,Yang Shu-Yuan,Jiao Li-Cheng.Research advances on structured compressive sensing.Acta Automatica Sinica,2013,39(12):1980-1995.
[9]孙玉宝,吴泽彬,吴敏,刘青山,联合低秩与稀疏先验的高光谱图像压缩感知重建[J].电子学报,2014,42(11):2221-2224.
[10]雷威,基于张量分解的高光谱图象压缩技术研究[D].哈尔滨:哈尔滨工业大学,2012.
[2]王忠美,杨晓梅,顾行发.张量组稀疏表示的高光谱图像去噪算法[J],测绘学报,2017,46(5):614-622.DOI:10.11947/j.AGCS.2017.20150403.WANG Zhongmei,YANG Xiaomei,GU Xingfa.Hyperspectral Image Denoising Based on Tensor Group Sparse Representation[J].Acta Geodaetica et Cartographica Sinica,2017,46(5):614-622.DOI:10.11947/j.AGCS.2017.20150403.
[3]刘亚楠,涂铮铮,罗斌,基于反馈稀疏约束的非负张量分解算法[J],计算机应用,2013,33(10):2871-2873.
[4]万晨坤,王斌,基于切片映射张量分析的高光谱图像压缩[J].自然科学,2015,54(6):696-705.
[5]王磊,王斌,张立明,基于张量分析和小波包变换的高光谱图像压缩[J].自然科学,2013,52(3):371-379.
[6]Tamara G.Kolda,Brett W.Bader,Tensor Decompositions and Applications.2009 Society for Industrial and Applied Mathematics.SIAM REVIEW,2009,51(3),pp.455-500.
[7]吴倩,张荣,徐大卫,基于稀疏表示的高光谱数据压缩算法[J].电子与信息学报,2015,37(1),78-84.
[8]Liu Fang,Wu Jiao,Yang Shu-Yuan,Jiao Li-Cheng.Research advances on structured compressive sensing.Acta Automatica Sinica,2013,39(12):1980-1995.
[9]孙玉宝,吴泽彬,吴敏,刘青山,联合低秩与稀疏先验的高光谱图像压缩感知重建[J].电子学报,2014,42(11):2221-2224.
[10]雷威,基于张量分解的高光谱图象压缩技术研究[D].哈尔滨:哈尔滨工业大学,2012.