摘要
高光谱解混旨在从盲源分离场景中识别出物质(端元)光谱特征和空间分布(丰度)特征。针对高光谱图像中存在大量混合像元降低解混的精度,以及当高光谱数据受到噪声污染时难以估计端元的准确数目等问题,本文提出一种将低秩松弛和可分离总变分先验信息相结合的线性混合模型。该方法首先利用对数函数的局部相似性对基于核范数的低秩表达式进行松弛,抑制次要分量;然后将各向异性总变分重新定义为可分离表达式,以平滑光谱特征和空间丰度特征;最后设计一组高效的求解器得到闭式解。实验结果表明,所提出的解混模型能有效地提升解混精度的同时也能抑制噪声,验证了该模型的有效性。
Hyperspectral unmixing aims to identify the spectral characteristics of substances(endmembers)and spatial distribution(abundance)features of substances(end-elements)from a blind source separation scenario.To address the challenges posed by a large number of mixed pixels in hyperspectral images,which can reduce unmixing accuracy,and the difficulty in accurately estimating the number of endmembers when hyperspectral data is contaminated with noise,a hyperspectral unmixing model that combines low-rank relaxation and separable total variation prior information is pro-posed in this paper.Firstly,the local similarity of the logarithmic function is utilized to relax the nuclear norm-based low-rank expression,thereby suppressing minor components.Then,the anisotropic total variation is redefined as a separa-ble expression to smooth the spectral characteristics and spatial abundance features.Finally,a set of efficient solvers is designed to obtain a closed-form solution.The experimental results show that the proposed unmixing model can effective-ly improve the unmixing accuracy while suppressing the noise,which verifies the effectiveness of the model.
作者
杨飞霞
李正
董贤达
马飞
YANG Fei-xia;LI Zheng;DONG Xian-da;MA Fei(School of Electrical and Control Engineering,Liaoning Technical University,Huludao 125105,China;School of Electronic and Information Engineering,Liaoning Technical University,Huludao 125105,China)
出处
《激光与红外》
北大核心
2025年第4期630-640,共11页
Laser & Infrared
基金
辽宁省科技厅自然科学基金计划面上项目(No.2023-MS-314)
辽宁省教育厅基本科研创新发展项目(No.LJ242410147006)资助。
关键词
高光谱
解混
对数低秩
可分离总变分
hyperspectral
unmixing
logarithmic low rank
separable total variation
