首页|基于结构化特征重构的高光谱图像分类

基于结构化特征重构的高光谱图像分类

扫码查看
原文链接
  • 万方数据
  • 维普
特征提取是高光谱图像分类的关键.现有分类方法在特征提取时,往往忽略特征的信息保有量和空间分布等因素,导致输出的特征可能面临低信息保有量与无序分布等问题,预测结果不佳.为此,本文提出一种基于结构化特征重构的高光谱图像分类方法,能够有效地减少特征提取过程中信息丢失,提高信息保有量,并充分考虑特征的空间分布,增强特征的判别性.借鉴重构思想以及自表达理论,建立结构特征重构的特征表示模型,可提升图像信息的利用率,并描述反映有序分布的结构信息.针对建立的多变量模型,设计一种基于交替更新的优化策略来求解模型.利用支持向量机来对特征进行分类计算和标签预测.利用Salinas、Pavia Center、Botswana以及Houston数据进行实验验证,结果表明,本文算法优于现有的分类模型,在OA(Overall Accuracy)、AA(Average Accuracy)以及Kappa系数等指标上平均提升了2.6%、3.9%、3.3%.
Structure-Wise Feature Reconstruction for Hyperspectral Image Classification
Feature extraction is a key operation for hyperspectral image(HSI)classification.For current classification approaches,they usually ignore the information preservation and spatial distribution in feature extraction,which may export features with low information utilization and disordered distribution,generating unsatisfactory prediction results.To remedy such deficiencies,a novel method based on structure-wise feature reconstruction is proposed for the HSI classification.This method can reduce the information loss and improve the information preservation during the process of feature extraction.In addition,the distribution is also fully considered to enhance the discriminability and separability.In this proposed meth-od,considering the reconstruction idea and the self-expression theory,a structure-wise feature reconstruction model is con-structed to extract the features of the HSI,which can improve the information utilization of original information from the HSI and describe the structure reflecting the well-ordered distribution.Here,an optimization with alternative updating is pre-sented to solve the above constructed model.The support vector machine is finally used to classify the extracted features and predict the labels of the HSI.The Salinas,Pavia Center,Botswana,and Houston datasets are used for experimental vali-dation.Results show that the proposed method achieves the better classification performance compared with some state-of-the-art approaches,which is averagely higher 2.6%,3.9%,3.3%at OA(Overall Accuracy),AA(Average Accuracy),and Kappa indexes.

hyperspectral image classificationinformation preservationstructure-wise feature reconstructionfea-ture distributionself-representationmodel optimizationsupport vector machine

邢长达、汪美玲、徐雍倡、王志胜

展开 >

中国矿业大学信息与控制工程学院,江苏 徐州 221116

南京航空航天大学计算机科学与技术学院,江苏 南京 211106

南京航空航天大学自动化学院,江苏 南京 211106

高光谱图像分类 信息保有量 结构化特征重构 特征分布 自表达 模型优化 支持向量机

国家自然科学基金国家自然科学基金中国博士后科学基金中央引导地方科技发展专项资金项目

62101247621061042022T1503202021Szvup063

2024

10.12263/DZXB.20230077

电子学报
中国电子学会

电子学报

CSTPCD北大核心
影响因子：1.237
ISSN：0372-2112
年,卷(期)：2024.52(9)