摘要
针对高光谱图像分类中空间及光谱信息利用不充分的问题,提出一种改进的空谱联合协同表征分类算法。通过获取训练像素与测试像素的欧式距离得到光谱信息,计算测试像素与训练像素的空间信息,结合空间信息与光谱信息建立空谱联合表征分类模型,采用最小残差法实现高光谱图像分类。实验结果表明,该算法在Indian Pines和Pavia University数据集上的分类精度分别达到98.36%和97.93%,优于传统高光谱图像分类算法。
Aiming at the problem of insufficient utilization of spatial and spectral information in hyperspectral image classification,an improved classification algorithm for coherent representation of space spectrum was proposed.The spectral information was obtained by obtaining the Euclidean distance between the training pixel and the test pixel.The spatial information of the test pixel and the training pixel was calculated.The spatial information and the spectral information were combined to establish a spatial correlation constellation classification model,and the minimum residual was used.The classification of hyperspectral images was then achieved.Experimental results show that the classification accuracy of the proposed algorithm on Indian Pines and Pavia University data sets is 98.36%and 97.93%,respectively,and it is superior to the traditional hyperspectral image classification algorithm.
作者
刘颖
刘蕊
李大湘
杨凡超
LIU Ying;LIU Rui;LI Da-xiang;YANG Fan-chao(College of Communication and Information Engineering,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;Laboratory of Spectral Imaging Technique,Xi’an Institute of Optics and Precision Mechanics,Chinese Academy of Sciences,Xi’an 710119,China;Ministry of Public Security Key Laboratory of Electronic Information Application Technology for Scene Investigation,Xi’an University of Posts and Telecommunications,Xi’an 710121,China)
出处
《计算机工程与设计》
北大核心
2020年第3期815-820,共6页
Computer Engineering and Design
基金
陕西省国际合作交流基金项目(2017KW-013)
国家自然科学基金项目(61571361、61102095)
西安邮电大学研究生创新基金项目(CXJJLY2018036)。
关键词
高光谱图像分类
信息联合
协同表征
空间正则化
谱空间信息
hyperspectral image classification
information union
collaborative representation
spatial regularization
spectral space information
