基于光谱和纹理特征的高光谱图像分类
投稿时间:2023-01-01  修订日期:2023-04-27  点此下载全文
引用本文:
摘要点击次数: 46
全文下载次数: 0
作者单位邮编
朱萌* 国网江苏省电力有限公司 210000
中文摘要:针对高光谱图像分类技术利用空间信息不足的问题,提出了一种光谱特征和纹理特征相结合的高光谱图像分类方法。通过二维Gabor小波提取高光谱图像纹理特征,利用函数型数据分析(FDA)框架分析高光谱数据,采用三次B样条基系统生成光谱特征和纹理特征的函数型数据,结合函数主成分分析(FPCA)提取每个像素的函数主成分(FPC),运用概率SVM分别对光谱特征和纹理特征进行分类。通过实验调参找到光谱特征和纹理特征的最佳参数组合,从而提高分类精度。通过在两个具有不同空间分辨率的高光谱图像数据集上进行实验,分析了参数的变化对分类精度的影响,并与其他同类方法相比较,随机选择5%的样本和10%的样本作为训练样本的总体精确度(OA)较EMAP+SVM方法分别提高了1.39%和3.87%。
中文关键词:高光谱图像  图像分类  纹理特征  光谱特征  空间信息
 
Hyperspectral Image Classification based on Spectral and Texture Features
Abstract:A hyperspectral image classification method based on the combination of spectral features and texture features is proposed to solve the problem of using insufficient spatial information in hyperspectral image classification technology. The texture features of hyperspectral images are extracted by two-dimensional Gabor wavelet, hyperspectral data are analyzed by functional data analysis (FDA) framework, functional data of spectral features and texture features are generated by cubic B-spline basis system, functional principal component analysis (FPCA) is used to extract the functional principal component (FPC) of each pixel, and probabilistic SVM is used to classify spectral features and texture features respectively. The best parameter combination of spectral features and texture features is found by adjusting parameters in experiments, so as to improve the classification accuracy. Through experiments on two hyperspectral image datasets with different spatial resolutions, the influence of parameter changes on classification accuracy is analyzed. Compared with other similar methods, the overall accuracy (OA) of randomly selecting 5% samples and 10% samples as training samples is 1.39% and 3.87% higher than that of EMAP+SVM respectively.
keywords:hyperspectral image  Image classification  Texture features  Hyperspectral data  spatial information
查看全文   查看/发表评论   下载pdf阅读器