高光谱遥感数据可以提供更加丰富的地物信息,但因其数据维度高、冗余性强等特点导致传统分类方法效率低下.针对此问题本文提出一种改进的核-主成分分析(kernel-principal component analysis,K-PCA)与概率神经网络(probabilistic neural network,PNN)结合的快速高光谱遥感分类算法.首先提出一种最近邻的样本选择方法,用以筛选更具代表性的地物光谱数据;其次提出一种基于半数重采样的主成分优选策略,有效去除噪声并保留光谱本质特征,大幅度降低数据维度;最后融合K-PCA的非线性降维特性与PNN的最优贝叶斯分类能力进行地物识别.在利用AVIRIS高光谱数据集的验证实验中,本算法不仅将分类精度提升至89.9%,较传统方法提升显著,且运算效率大幅提升.结果表明该算法在兼顾分类精度与实时性的高光谱地物识别场景中凸显优势,为遥感大数据智能处理提供了高效解决方案.
Hyperspectral remote sensing data can provide more abundant information about ground objects, but its high data dimension and strong redundancy also lead to low efficiency of traditional classification methods. To address this issue, this paper proposes an enhanced rapid hyperspectral remote sensing classification algorithm combining kernel-principal component analysis(K-PCA)and probabilistic neural network(PNN). Firstly, a nearest neighbor sample selection method is proposed to screen more representative ground object spectral data. Secondly, a principal component selection strategy based on half resampling is proposed to effectively remove noise and retain the essential spectral features, significantly- DOI:10.3969/j.issn.1000-1565.2025.04.002一种改进的K-PCA与PNN结合的快速高光谱遥感分类算法简萌1,陈旭凤2,鲁军2,郝敏钗2( 1.北京工业大学 信息科学技术学院,北京 100124;2.河北工业职业技术大学 智能制造学院,河北 石家庄 050091)摘 要:高光谱遥感数据可以提供更加丰富的地物信息,但因其数据维度高、冗余性强等特点导致传统分类方法效率低下.针对此问题本文提出一种改进的核-主成分分析(kernel-principal component analysis,K-PCA)与概率神经网络(probabilistic neural network,PNN)结合的快速高光谱遥感分类算法.首先提出一种最近邻的样本选择方法,用以筛选更具代表性的地物光谱数据;其次提出一种基于半数重采样的主成分优选策略,有效去除噪声并保留光谱本质特征,大幅度降低数据维度;最后融合K-PCA的非线性降维特性与PNN的最优贝叶斯分类能力进行地物识别.在利用AVIRIS高光谱数据集的验证实验中,本算法不仅将分类精度提升至89.9%,较传统方法提升显著,且运算效率大幅提升.结果表明该算法在兼顾分类精度与实时性的高光谱地物识别场景中凸显优势,为遥感大数据智能处理提供了高效解决方案.关键词:高光谱遥感数据;地物识别;核-主成分分析;概率神经网络;半数重采样中图分类号:O433 文献标志码:A 文章编号:1000-1565(2025)04-0343-09A rapid hyperspectral remote sensing classification algorithm combining improved K-PCA and PNNJIAN Meng1,CHEN Xufeng2, LU Jun2, HAO Minchai2(1.School of Information Science and Technology,Beijing University of Technology,Beijing 100124,China; 2.School of Intelligent Manufacturing, Hebei Vocational University of Industry and Technology, Shijiazhuang 050091, China)Abstract: Hyperspectral remote sensing data can provide more abundant information about ground objects, but its high data dimension and strong redundancy also lead to low efficiency of traditional classification methods. To address this issue, this paper proposes an enhanced rapid hyperspectral remote sensing classification algorithm combining kernel-principal component analysis(K-PCA)and probabilistic neural network(PNN). Firstly, a nearest neighbor sample selection method is proposed to screen more representative ground object spectral data. Secondly, a principal component selection strategy based on half resampling is proposed to effectively remove noise and retain the essential spectral features, significantly- 收稿日期:2024-09-11;修回日期:2025-05-06 基金项目:中央引导地方科技发展资金项目(216Z1004G);河北省高校硬质合金切削材料应用技术研发中心基金;河北工业职业技术大学博士基金项目(bz202205) 第一作者:简萌(1987—),女,蒙古族,北京工业大学教授,博士,主要从事数据挖掘、多媒体计算研究.E-mail:jianmeng648@163.com 通信作者:陈旭凤(1991—),女,河北工业职业技术大学讲师,主要从事深度学习技术研究.E-mail:xufengchen_gyznzz@163.com 第4期简萌等:一种改进的K-PCA与PNN结合的快速高光谱遥感分类算法河北大学学报(自然科学版) 第45卷reducing the data dimension. Finally, by integrating the nonlinear dimensionality reduction characteristics of K-PCA and the optimal Bayesian classification ability of PNN, in the verification experiment using the AVIRIS hyperspectral dataset, the algorithm not only improves the classification accuracy to 89.9%, a significant improvement over traditional methods, but also greatly enhances the operational efficiency. Experiments show that this algorithm demonstrates outstanding advantages in hyperspectral ground object recognition scenarios where both classification accuracy and real-time performance need to be considered, providing an efficient solution for intelligent processing of remote sensing big data.
[1] SUN Q, CHEN L P, GU X H, et al. Estimation of canopy nitrogen nutrient status in lodging maize using unmanned aerial vehicles hyperspectral data[J]. Ecol Inform, 2023, 78: 102315. DOI: 10.1016/j. ecoinf.2023.102315.
[2] WANG Y, MA H B, WANG J Z, et al. Hyperspectral monitor of soil chromium contaminant based on deep learning network model in the Eastern Junggar coalfield[J]. Spectrochim Acta Part A Mol Biomol Spectrosc, 2021, 257: 119739. DOI: 10.1016/j.saa.2021. 119739.
[3] SHU M Y, DONG Q Z, FEI S P, et al. Improved estimation of canopy water status in maize using UAV-based digital and hyperspectral images[J]. Comput Electron Agric, 2022, 197: 106982. DOI: 10.1016/j.compag.2022.106982.
[4] 张俊,谭耀鑫,卢静静,等.基于深度学习的高光谱图像去噪综述[J].南昌工程学院学报, 2024, 43(3): 88-96.
[5] WANG W X, LIU L M, ZHANG T X, et al. Hyper-ES2T: Efficient Spatial-Spectral Transformer for the classification of hyperspectral remote sensing images[J]. Int J Appl Earth Obs Geoinf, 2022, 113: 103005. DOI: 10.1016/j.jag.2022.103005.
[6] SEIFI M, AHMADI A, NEYSHABOURI M R, et al. Remote and Vis-NIR spectra sensing potential for soil salinization estimation in the eastern coast of Urmia hyper saline lake, Iran[J]. Remote Sens Appl Soc Environ, 2020, 20: 100398. DOI: 10.1016/j.rsase.2020.100398.
[7] 谭宏婕,邱昆峰,刘洪成,等.西秦岭李坝造山型金矿床围岩蚀变特征:基于高分五号02星(GF-5B)星载高光谱数据信息提取[J]. 岩石学报, 2024, 40(6): 1784-1800. DOI: 10. 18654/1000-0569/2024.06.06.
[8] 张娟娟,牛圳,马新明,等.基于离散小波的土壤全氮高光谱特征提取与反演[J].光谱学与光谱分析, 2023, 43(10): 3223-3229.
[9] 聂萍.基于高光谱的农作物遥感图像降维和分类[D].哈尔滨:黑龙江大学, 2024. DOI: 10.27123/d.cnki.ghlju.2024.000559.
[10] 周峥,杨宇,张敢,等.基于自监督学习的高光谱图像降维算法[J].激光与光电子学进展, 2024, 61(12): 1237001. DOI: 10.3788/LOP231646.
[11] 刘敬,李银桥,刘逸.主动学习联合聚类分组网络的高光谱遥感图像分类[J].光学 精密工程, 2024, 32(9): 1395-1407.
[12] KAIB M T H, KOUADRI A, HARKAT M F, et al. Improving kernel PCA-based algorithm for fault detection in nonlinear industrial process through fractal dimension[J]. Process Saf Environ Prot, 2023, 179: 525-536. DOI: 10.1016/j.psep.2023.09.010.
[13] WANG S H, ZHAN T M, CHEN Y, et al. Multiple sclerosis detection based on biorthogonal wavelet transform, RBF kernel principal component analysis, and logistic regression[J]. IEEE Access, 2017, 4: 7567-7576.
[14] ATTOURI K, MANSOURI M, HAJJI M, et al. Improved fault detection based on kernel PCA for monitoring industrial applications[J]. J Process Contr, 2024, 133: 103143. DOI: 10.1016/j.jprocont.2023.103143.
[15] REN Z L, JIANG Y C, YANG X B, et al. Learnable faster kernel-PCA for nonlinear fault detection: Deep autoencoder-based realization[J]. J Ind Inf Integr, 2024, 40: 100622. DOI: 10.1016/j.jii.2024.100622.
[16] 王团辉,王超,李岳峰,等.基于KPCA-KNN算法的边坡稳定性预测[J].化工矿物与加工, 2023, 52(12): 52-58. DOI: 10.16283/j.cnki.hgkwyjg.2023.12.008.
[17] KONG D D, CHEN Y J, LI N, et al. Tool wear monitoring based on kernel principal component analysis and v-support vector regression[J]. Int J Adv Manuf Technol, 2017, 89(1): 175-190. DOI: 10.1007/s00170-016-9070-x.
[18] 王彩玲,张静,王洪伟,等.一种波段聚类和多尺度结构特征融合的高光谱图像分类模型[J]. 光谱学与光谱分析, 2024, 44(1): 258-265. DOI: 10.3964/j.issn.1000-0593(2024)01-0258-08.
[19] 翟苏巍,李文云,周成,等.基于改进概率神经网络的储能电池荷电状态估计[J].智慧电力, 2024, 52(2): 94-100.
[20] 黄赵军,苏建徽,解宝,等.基于模糊C均值聚类和概率神经网络的PEMFC故障诊断方法研究[J].太阳能学报, 2024, 45(1): 475-483. DOI: 10.19912/j.0254-0096.tynxb.2022-1480.
[21] RUTKOWSKA D, DUDA P, CAO J, et al. The L2 convergence of stream data mining algorithms based on probabilistic neural networks[J]. Information Sciences, 2023, 631: 346-368. https://www.nstl.gov.cn/paper_detail.html?id=0e43d5c345d8d98f7d5c6172e0273543.
[22] LI Q B, ZHONG J, DU J Q, et al. Probabilistic neural network-based flexible estimation of lithium-ion battery capacity considering multidimensional charging habits[J]. Energy, 2024, 294: 130881. DOI: 10.1016/j.energy.2024.130881.
[23] EL-DABAA S A, METWALLI F I, AMIN A T, et al. Prediction of porosity and water saturation using a probabilistic neural network for the Bahariya Formation, Nader Field, north western desert, Egypt[J]. J Afr Earth Sci, 2022, 196: 104638. DOI: 10.1016/j.jafrearsci.2022.104638.
[24] HOYA T. Reducing the number of centers in a probabilistic neural network via applying the first neighbor means clustering algorithm[J]. Array, 2022, 14: 100161. DOI: 10.1016/j.array.2022.100161.
[25] MASUDUL ISLAM S, KUMAR V, KUMAR S, et al. Spectral mixture analysis of AVIRIS-NG hyperspectral data for material identification and classification for the part of Kolkata city[J]. Adv Space Res, 2024, 73(2): 1560-1572. DOI: 10.1016/j.asr.2022.12.044.
[26] PALACIOS S L, THOMPSON D R, KUDELA R M, et al. Seasonal and Inter-Annual Patterns of Chlorophyll and Phytoplankton Community Structure in Monterey Bay, CA Derived from AVIRIS Data During the 2013-2015 HyspIRI Airborne Campaign[C] //American Geophysical Union, Ocean Sciences Meeting. 2016: abstract# EC34D-1215.
[27] MONDAL S, GUHA A, KUMAR PAL S. Support vector machine-based integration of AVIRIS NG hyperspectral and ground geophysical data for identifying potential zones for chromite exploration-A study in Tamil Nadu, India[J]. Adv Space Res, 2024, 73(2): 1475-1490. DOI: 10.1016/j.asr.2022.04.048.
[28] Hyperspectral Remote Sensing Scenes[EB/OL]. [2024-10-01]. https://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes. (
