基于ADMM和深度生成先验的高光谱解混方法  

A hyperspectral unmixing method based on ADMM and deep generative prior

作　　者：赵敏 陈捷[1,2] ZHAO Min;CHEN Jie(School of Marine Science and Technology,Northwestern Polytechnical University,Xi’an 710072,China;Research and Development Institute,Northwestern Polytechnical University in Shenzhen,Shenzhen 518057,China)

机构地区：[1]西北工业大学航海学院,陕西西安710072 [2]西北工业大学深圳研究院,广东深圳518057

出　　处：《哈尔滨工程大学学报》2024年第9期1639-1647,共9页Journal of Harbin Engineering University

基　　金：国家自然科学基金项目(62171380);深圳市科创委项目(JCYJ20220530161606014).

摘　　要：混合像元的存在制约了高光谱图像分类和目标检测的精度,为了提高混合像元分解的精度,精确地分析混合像元中的组成成分,本文提出将优化方法和深度生成先验结合的高光谱解混方法,实现数据驱动和模型驱动的有机结合。近年来,基于深度神经网络的处理方法被广泛使用在高光谱解混任务中。但是该类方法是“黑盒子”,缺乏物理可解释性。传统的基于数学优化的高光谱解混方法,通过使用人工设计的先验项引入图像内含信息,提高解混精度。但是对于复杂的先验项,求解方法复杂,且并不是所有先验信息都可以用数学模型表示出来。所以本文提出一结合交替方向乘子法优化算法和深度生成先验的高光谱解混方法,联合使用数学优化和深度方法的优越性。首先使用ADMM算法将数据拟合项和生成先验项进行解耦,对于生成先验,使用传统解混方法获得的丰度预训练变分自编码器网络,并将解码器作为生成器。本文同时使用人工合成数据和真实遥感数据验证所提出方法的有效性。The presence of mixed pixels restricts the accuracy of hyperspectral image classification and object detec-tion.To improve the accuracy of mixed pixel decomposition and accurately analyze the composition of mixed pixels,this study proposes a hyperspectral unmixing method that combines an optimization method with deep generative pri-ors,thereby achieving an organic combination of data-driven and model-driven approaches.In recent years,deep neural networks have been widely used in hyperspectral unmixing;however,these methods often act as“black bo-xes”lacking physical interpretability.Conversely,traditional mathematically optimized hyperspectral unmixing methods use manually selected priors to introduce intrinsic information and improve the accuracy of results.Howev-er,computing a complex regularizer needs difficult algorithms,and some information cannot be modeled mathemati-cally.In this study,we propose a hyperspectral unmixing method that integrates the alternating direction method of multipliers(ADMMs)with deep generative priors to combine the strengths of both approaches.Specifically,we use ADMM to decompose the data-fitting term and generative priors,and the decoder of a VAE pre-trained by abun-dance calculated using conventional methods is applied as the generator.This study uses simulated and real remote-sensing datasets to evaluate the effectiveness of the proposed method.

关 键 词：遥感 高光谱图像 混合像元 高光谱解混 深度先验 交替方向乘子法 生成模型 变分自编码器 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]