首页 | 本学科首页   官方微博 | 高级检索  
     

基于稀疏表示及光谱信息的高光谱遥感图像分类
引用本文:宋相法, 焦李成. 基于稀疏表示及光谱信息的高光谱遥感图像分类[J]. 电子与信息学报, 2012, 34(2): 268-272. doi: 10.3724/SP.J.1146.2011.00540
作者姓名:宋相法  焦李成
作者单位:1. 西安电子科技大学智能感知与图像理解教育部重点实验室 西安710071;河南大学计算机与信息工程学院 开封475004
2. 西安电子科技大学智能感知与图像理解教育部重点实验室 西安710071
基金项目:国家自然科学基金,高等学校学科创新引智计划(111计划),中央高校基本科研业务费专项资金
摘    要:该文结合稀疏表示及光谱信息提出了一种新的高光谱遥感图像分类算法。首先提出利用高光谱遥感图像数据集构造学习字典,然后根据学习字典计算每个像元的稀疏系数,从而获得像元的稀疏表示特征,最后根据稀疏表示特征和光谱信息分别构造随机森林,通过投票机制得到最终的分类结果。在AVIRIS高光谱遥感图像上的实验结果表明:该文所提方法能够提高分类效果,且其分类总精度和Kappa系数要高于光谱信息和稀疏表示特征方法。

关 键 词:图像处理   高光谱遥感图像   稀疏表示   分类   随机森林
收稿时间:2011-06-02
修稿时间:2011-10-31

Classification of Hyperspectral Remote Sensing Image Based on Sparse Representation and Spectral Information
Song Xiang-Fa, Jiao Li-Cheng. Classification of Hyperspectral Remote Sensing Image Based on Sparse Representation and Spectral Information[J]. Journal of Electronics & Information Technology, 2012, 34(2): 268-272. doi: 10.3724/SP.J.1146.2011.00540
Authors:Song Xiang-fa    Jiao Li-cheng
Affiliation:Song Xiang-fa①② Jiao Li-cheng① ①(Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University,Xi,an 710071,China) ②(School of Computer and Information Engineering,Henan University,Kaifeng 475004,China)
Abstract:This paper presents a novel classification algorithm of hyperspectral remote sensing image based on sparse representation and spectral information.First,a learning dictionary is obtained based on hyperspectral remote sensing image data set,and then the sparse coefficient of each pixel is calculated according to the learning dictionary.As a result,sparse representation feature is obtained.Finally,random forests are respectively constructed based on sparse representation feature and spectral information,and the classification result is decided by voting strategy.Experiments on AVIRIS hyperspectral remote sensing image justify the effectiveness of the algorithm.The experimental results indicate that the proposed method has better performance than methods based on spectral and sparse representation respectively,and has a higher overall accuracy and Kappa coefficient.
Keywords:Image processing  Hyperspectral remote sensing image  Sparse representation  Classification  Random forests
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《电子与信息学报》浏览原始摘要信息
点击此处可从《电子与信息学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号