陈志超, 张正, 刘昌华,等.基于多线性稀疏主成分的高光谱影像特征提取[J].河南理工大学学报（自然科学版）,2020,39(4):54-60.

CHEN Z C, ZHANG Z , LIU C H,et al.Feature extraction of hyperspectral image based on multilinear sparseprincipal components[J].Journal of Henan Polytechnic University(Natural Science) ,2020,39(4):54-60.

基于多线性稀疏主成分的高光谱影像特征提取

陈志超1, 张正1, 刘昌华1, 周亚文2, 芦俊俊1, 王春阳1

1.河南理工大学测绘与国土信息工程学院，河南焦作 454000;2.北京吉威时代软件股份有限公司，北京 100194

摘要:高光谱影像特征提取有助于提高高光谱数据的应用效率和精度。针对基于向量的特征提取算法无法充分利用高光谱影像立方体空间结构信息这一缺点，本文提出在所有张量模式 中执行稀疏降维的多线性稀疏主成分分析（MSPCA）算法，以中国嘉兴典型村庄和美国内华达州Curprite矿区高光谱影像为原始数据，运用主成分分析（PCA）、空间主成分分析（SPCA）和多线性判别分析（MPCA） 3种特征提取方法对比分析所提算法特征提取后的分类精度。结果表明，利用MSPCA进行特征提取得到的分类精度均优于其他方法，在两个试验区的总体分类精度分别达到96. 36%和95. 00%。

关键词:高光谱影像;多线性稀疏主成分分析;特征提取

doi:10.16186/j.cnki.1673-9787.2020.4.7

基金项目:河南省自然科学基金资助项目(182300410111 )；河南省高等学校重点科研项目(18A420001 )；河南省智慧中原地理信息 技术协同创新中心开放课题(2016A002)

收稿日期:2019-11-28 00:00:00

修回日期:2020-01-30 00:00:00

出版日期:2020/07/15

Feature extraction of hyperspectral image based on multilinear sparseprincipal components

CHEN Zhichao1, ZHANG Zheng1, LIU Changhua1, ZHOU Yawen2, LU Junjun1, WANG Chunyang1

1.College of Surveying and Land Information Engineering， Henan Polytechnic University， Jiaozuo  454000 ， Henan， China;2.Beijing GEOWAY Software Co. ， Ltd. ， Beijing  100194 ， China

Abstract:The feature extraction of hyperspectral image helps to improve the application efficiency and accuracy of hyperspectral data. Considering the disadvantage that vector based feature extraction algorithm could not make full use of the cube spatial structure information of hyperspectral image， the multilinear sparse principal component analysis（ MSPCA） algorithm was proposed to perform sparse dimensionality reduction in all tensor modes. Based on the hyperspectral images of typical villages in Jiaxing， China， and the currite mining area in Nevada， USA， three feature extraction methods i. e. ， principal component analysis （ PCA ） ， spatial principal component analysis （ SPCA ） and multi-linear discriminant analysis （ MPCA ） ， were used to compare and analyze the classification accuracy of the proposed algorithm after feature extraction. The results showed that the classification accuracy of feature extraction obtained by MSPCA was better than that of the other three methods， and the overall classification accuracy of the proposed algorithm in the two experimental areas was 96. 36% and 95.00% respectively.

Key words:hyperspectral image;multilinear sparse principal component analysis;feature extraction

基于多线性稀疏主成分的高光谱影像特征提取_陈志超.pdf