基于二次平滑和特征加权的高光谱图像分类

doi:10.13474/j.cnki.11-2246.2025.0610

摘要/Abstract

摘要： 针对多种基于图像滤波的空谱联合分类方法在去噪的同时难以保留图像弱边缘的问题,本文提出了一种基于二次平滑和特征加权的高光谱图像分类方法。首先通过最小最大规范化对原始高光谱图像进行预处理,其次采用主成分分析对高光谱图像进行降维,再次运用加窗域变换递归滤波在得到弱化噪声的特征图像的同时保留弱边缘,然后通过L0梯度最小化对特征图像进行二次平滑进一步抑制噪声并增强边缘,并基于方差对特征图像进行加权,最后采用支持向量机进行分类。在两个数据集上进行试验,该方法的分类精度相比基于光谱特征的方法分别提升了14.06%和25.75%,相比于该领域多种滤波算法分别提升0.76%～4.3%和1.5%～5.69%,且分类结果更能反映真实地物类别。

关键词: 高光谱图像分类, 主成分分析, 加窗域变换递归滤波, L0梯度最小化, 特征加权

Abstract: A hyperspectral image classification method based on two-step smoothing and feature weighting is proposed to address the problem of various image filtering based spatial spectral joint classification methods being difficult to preserve weak edges of the image while denoising. Firstly, the original hyperspectral image is preprocessed by minimum maximum normalization, and then principal component analysis is used to reduce the dimensionality of the hyperspectral image. Next, using windowed domain transformation recursive filtering to obtain feature images with weakened noise while preserving weak edges, and then smoothing the feature images again through L0 gradient minimization to further suppress noise and enhance edges. After that, each feature image is weighted by variance. Finally, support vector machine is used for classification. Experiments were conducted on two datasets, and the classification accuracy of this method improved by 14.06% and 25.75% compared to spectral feature-based methods, and by 0.76%～4.3% and 1.5%～5.69% compared to various filtering algorithms in this field. Moreover, the classification results better reflect the true land cover categories.

Key words: hyperspectral image classification, principal component analysis, windowed domain transform recursive filtering, L0 gradient minimization smoothing, feature weighting

中图分类号:

许淇, 杨嘉葳, 王继燕. 基于二次平滑和特征加权的高光谱图像分类[J]. 测绘通报, 2025, 0(6): 55-61.

XU Qi, YANG Jiawei, WANG Jiyan. Hyperspectral image classification based on two-step smoothing and feature weighting[J]. Bulletin of Surveying and Mapping, 2025, 0(6): 55-61.

参考文献

[1] LU Bing,DAO P D,LIU Jiangui,et al.Recent advances of hyperspectral imaging technology and applications in agriculture[J].Remote Sensing,2020,12(16):2659.
[2] SCAFUTTO R D M,DE SOUZA FILHO C R,DE OLIVEIRA W J.Hyperspectral remote sensing detection of petroleum hydrocarbons in mixtures with mineral substrates:implications for onshore exploration and monitoring[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,128:146-157.
[3] ZHANG Ning,WANG Yueting,ZHANG Xiaoli.Extraction of tree crowns damaged by Dendrolimus tabulaeformis Tsai et Liu via spectral-spatial classification using UAV-based hyperspectral images[J].Plant Methods,2020,16:135.
[4] ZHAO Jiale,ZHOU Bing,WANG Guanglong,et al.Camouflage target recognition based on dimension reduction analysis of hyperspectral image regions[J].Photonics,2022,9(9):640.
[5] GAN Yuhang,LUO Fulin,LIU Juhua,et al.Feature extraction based multi-structure manifold embedding for hyperspectral remote sensing image classification[J].IEEE Access,2017,5:25069-25080.
[6] REN Jiansi,WANG Ruoxiang,LIU Gang,et al.Partitioned relief-F method for dimensionality reduction of hyperspectral images[J].Remote Sensing,2020,12(7):1104.
[7] CUI Zhi,CAI Zhenhua.Feature extraction of hyperspectral images based on subspace band selection and transform-domain recursive filtering[J].Traitement Du Signal,2022,39(3):845-852.
[8] OU Xianfeng,WU Meng,TU Bing,et al.Multi-objective unsupervised band selection method for hyperspectral images classification[J].IEEE Transactions on Image Processing,2023,32:1952-1965.
[9] FARRELL M D,MERSEREAU R M.On the impact of PCA dimension reduction for hyperspectral detection of difficult targets[J].IEEE Geoscience and Remote Sensing Letters,2005,2(2):192-195.
[10] DU Qian,YOUNAN N H.Dimensionality reduction and linear discriminant analysis for hyperspectral image classification[M]//Knowledge-Based Intelligent Information and Engineering Systems.Berlin,Heidelberg:Springer Berlin Heidelberg,2008:392-399.
[11] SAI KISHORE K M,KUMAR BEHERA M,CHAKRAVARTY S,et al.Hyperspectral image classification using minimum noise fraction and random forest[C]//Proceedings of 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE).Bhubaneswar:IEEE,2020.
[12] KANG Xudong,XIANG Xuanlin,LI Shutao,et al.PCA-based edge-preserving features for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(12):7140-7151.
[13] WANG Xiaotao.Kronecker factorization-based multinomial logistic regression for hyperspectral image classification[J].IEEE Geoscience and Remote Sensing Letters,2021,19:5508005.
[14] XIA Junshi,GHAMISI P,YOKOYA N,et al.Random forest ensembles and extended multiextinction profiles for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(1):202-216.
[15] MELGANI F,BRUZZONE L.Classification of hyperspectral remote sensing images with support vector machines[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(8):1778-1790.
[16] CAO Xianghai,WANG Xiaozhen,WANG Da,et al.Spectral spatial hyperspectral image classification using cascaded Markov random fields[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2019,12(12):4861-4872.
[17] LI Changli,ZUO Hang,FAN Tanghuai.Hyperspectral image classification based on gray level co-occurrence matrix and local mean decomposition[C]//Proceedings of the 4th International Conference on Systems and Informatics (ICSAI).Hangzhou:IEEE,2017:1219-1223.
[18] DUAN Puhong,GHAMISI P,KANG Xudong,et al.Fusion of dual spatial information for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2021,59(9):7726-7738.
[19] HUANG Shiqi,LU Ying,WANG Wenqing,et al.Multi-scale guided feature extraction and classification algorithm for hyperspectral images[J].Scientific Reports,2021,11(1):18396.
[20] HADOUX X,JAY S,RABATEL G,et al.A spectral-spatial approach for hyperspectral image classification using spatial regularization on supervised score image[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(6):2361-2369.
[21] QU Shenming,LIU Xuan,LIANG Shengbin.Multi-scale superpixels dimension reduction hyperspectral image classification algorithm based on low rank sparse representation joint hierarchical recursive filtering[J].Sensors,2021,21(11):3846.
[22] ROY S K,KRISHNA G,DUBEY S R,et al.HybridSN:exploring 3-D-2-D CNN feature hierarchy for hyperspectral image classification[J].IEEE Geoscience and Remote Sensing Letters,2020,17(2):277-281.
[23] MOU Lichao,GHAMISI P,ZHU XIAO xiang.Deep recurrent neural networks for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(7):3639-3655.
[24] ZHANG Fan,BAI Jing,ZHANG Jingsen,et al.An optimized training method for GAN-based hyperspectral image classification[J].IEEE Geoscience and Remote Sensing Letters,2021,18(10):1791-1795.
[25] GASTAL E S L,OLIVEIRA M M.Domain transform for edge-aware image and video processing[J].ACM Transactions on Graphics,2011,30(4):1-12.
[26] XU Li,YAN Qiong,XIA Yang,et al.Structure extraction from texture via relative total variation[J].ACM Transactions on Graphics,2012,31(6):1-10.
[27] XU Li,LU Cewu,XU Yi,et al.Image smoothing via L0 gradient minimization[J].ACM Transactions on Graphics,2011,30(6):1-12.
[28] 崔宾阁,吴亚男,钟勇,等.高光谱图像滚动引导递归滤波与地物分类[J].遥感学报,2019,23(3):431-442.