电子测量与仪器学报

杨明莉,范玉刚,李宝芸.基于 LDA 和 ELM 的高光谱图像降维与分类方法研究[J].电子测量与仪器学报,2020,34(5):190-196

基于 LDA 和 ELM 的高光谱图像降维与分类方法研究

Research on dimensionality reduction and classification ofhyperspectral images based on LDA and ELM

DOI：

英文关键词:hyperspectral image extreme learning machine linear discriminant analysis dimensionality reduction classification

基金项目:

作者	单位
杨明莉	1. 昆明理工大学信息工程与自动化学院，2. 昆明理工大学云南省人工智能重点实验室，3. 云南省矿物管道输送工程技术研究中心
范玉刚	1. 昆明理工大学信息工程与自动化学院，2. 昆明理工大学云南省人工智能重点实验室，3. 云南省矿物管道输送工程技术研究中心
李宝芸	1. 昆明理工大学信息工程与自动化学院，2. 昆明理工大学云南省人工智能重点实验室，3. 云南省矿物管道输送工程技术研究中心

Author	Institution
Yang Mingli	1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology,2. Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology,3. Yunnan Mineral Pipeline Transportation Engineering and Technology Research Center
Fan Yugang	1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology,2. Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology,3. Yunnan Mineral Pipeline Transportation Engineering and Technology Research Center
Li Baoyun	1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology,2. Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology,3. Yunnan Mineral Pipeline Transportation Engineering and Technology Research Center

摘要点击次数: 723

全文下载次数: 1107

中文摘要:

高光谱图像具有波段多、波段间相关性强的特点,导致高光谱图像信息冗余,造成维数灾难、难以分类的问题,为此提出了一种基于线性判别分析(LDA)和极限学习机结合的高光谱图像降维分类方法。该方法首先通过 LDA 对高光谱数据进行降维处理,克服高光谱图像信息冗余等问题的同时,尽可能保留图像的特征信息;降低光谱图像维度后,采用极限学习机(ELM) 对高光谱遥感图像进行分类识别。所提方法应用于 Pavia University 和 Salinas 高光谱图像处理,分类精度分别达到了 98. 78%和 99. 94%,有效提升了高光谱图像的地物分类性能,具有较强的实用性。

英文摘要:

Hyperspectral images have the characteristics of multiple bands and strong correlation among bands, which leads to information redundancy of hyperspectral images, resulting in dimensionality disaster and difficulty in classification. Therefore, a dimensionality reduction classification method of hyperspectral images based on LDA and extreme learning machine is proposed. In this method, hyperspectral data are firstly processed by LDA for dimensionality reduction, so as to overcome the problem of hyperspectral image information redundancy and keep the image feature information as far as possible. After reducing the spectral image dimension, ELM is adopted to classify and identify hyperspectral remote sensing images. The method proposed is applied to Pavia University and Salinas hyperspectral image processing, and the classification accuracy reaches 98. 78% and 99. 94% respectively, which effectively improves the feature classification performance of hyperspectral images and has strong practicability.

查看全文查看/发表评论下载PDF阅读器