Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (3): 587-593    DOI: 10.11873/j.issn.1004-0323.2021.3.0587
数据与图像处理     
基于LFDA和GA-ELM的高光谱图像地物识别方法研究
李宝芸1(),范玉刚1,2,3(),杨明莉1
1.昆明理工大学 信息工程与自动化学院,云南 昆明 650500
2.云南省矿物管道输送工程技术研究中心,云南 昆明 650500
3.昆明理工大学 云南省人工智能重点实验室,云南 昆明 650500
Research on Feature Recognition Method of Hyperspectral Image based on LFDA and GA-ELM
Baoyun Li1(),Yugang Fan1,2,3(),Mingli Yang1
1.Faculty of Information Engineering & Automation,Kunming University of Science and Technology,Kunming 650500,China
2.Engineering Research Center for Mineral Pipeline Transportation,Kunming 650500,China
3.Yunnan Key Laboratory of Artificial Intelligence,Kunming University of Science and Technology,Kunming 650500,China
 全文: PDF(2523 KB)   HTML
摘要:

高光谱图像的高维特性和波段间的高相关性,导致高光谱图像地物识别问题研究中,面临着数据量大、信息冗余的问题,降低了高光谱图像的分类识别精度。针对以上问题,提出了基于局部保留降维(Local Fisher Discriminant Analysis,LFDA)结合遗传算法(Genetic Algorithm, GA )优化极限学习机(Extreme Learning Machine, ELM)的高光谱图像分类方法。首先,采用LFDA对高光谱图像数据进行降维处理,消除信息冗余并保留局部邻域内主要特征;然后用GA优化ELM,对降维处理后的特征样本进行分类,提高高光谱图像的分类识别精度。将该方法应用于Salinas和Pavia University高光谱图像的地物识别问题研究,分类精度分别达到了98.56%和97.11%,由此验证了该方法的有效性。

关键词: 高光谱图像降维极限学习机分类识别    
Abstract:

The high-dimensional characteristics of the hyperspectral image and the high correlation between the bands have led to the problem of large data volume and information redundancy in the study of the feature recognition of hyperspectral images, which reduces the classification and recognition accuracy of hyperspectral images. Aiming at the above problems, a hyperspectral image classification method based on Local Fisher Discriminant Analysis (LFDA) combined with Genetic Algorithm (GA) to optimize Extreme Learning Machine (ELM) is proposed. First, the LFDA is used to reduce the dimensionality of the hyperspectral image data to eliminate information redundancy and retain the main features in the local neighborhood; then use GA to optimize the ELM, classify the feature samples after the dimensionality reduction, and improve the classification and recognition of the hyperspectral image Precision. The method proposed in this paper is applied to the research on the feature recognition of hyperspectral images in Salinas and Pavia University. The classification accuracy reaches 98.56% and 97.11% respectively, which verifies the effectiveness of the method in this paper.

Key words: Hyperspectral image    Dimensionality reduction    Extreme learning machine    Classification recognition
收稿日期: 2019-12-17 出版日期: 2021-07-22
ZTFLH:  TP751.1  
基金资助: 云南省教育厅科学研究基金项目(2018JS019)
通讯作者: 范玉刚     E-mail: 1475052566@qq.com;ygfan@qq.com
作者简介: 李宝芸(1996-),女,重庆万州人,硕士研究生,主要从事图像处理、模式识别研究。E?mail:1475052566@qq.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
李宝芸
范玉刚
杨明莉

引用本文:

李宝芸,范玉刚,杨明莉. 基于LFDA和GA-ELM的高光谱图像地物识别方法研究[J]. 遥感技术与应用, 2021, 36(3): 587-593.

Baoyun Li,Yugang Fan,Mingli Yang. Research on Feature Recognition Method of Hyperspectral Image based on LFDA and GA-ELM. Remote Sensing Technology and Application, 2021, 36(3): 587-593.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.3.0587        http://www.rsta.ac.cn/CN/Y2021/V36/I3/587

图1  Salinas高光谱遥感影像
图2  Pavia University高光谱遥感影像
降维方式分类方式AA/%OA/%Kappa系数

不进行降维

SVM97.0296.870.972
ELM73.2973.110.736
GA-ELM85.5685.270.855

PCA

SVM95.1295.870.955
ELM95.6595.600.952
GA-ELM85.3785.620.863

LDA

SVM94.5695.500.958
ELM94.2295.620.962
GA-ELM86.3786.130.866

LFDA

SVM96.5696.500.958
ELM96.2296.620.962
GA-ELM97.3898.560.972
表1  Salinas数据集实验结果
降维方式分类方式AA/%OA/%Kappa系数

不进行降维

SVM96.1795.560.965
ELM53.4853.920.545
GA-ELM86.3786.670.862

PCA

SVM94.3793.670.945
ELM92.0391.040.922
GA-ELM95.8994.130.944

LDA

SVM93.3396.440.945
ELM93.1295.110.947
GA-ELM95.9295.420.956

LFDA

SVM94.5096.600.930
ELM95.5696.000.946
GA-ELM96.2397.110.964
表2  Pavia University数据集实验结果
图3  不同方法在Salinas数据集的分类结果图
图4  不同方法在Pavia University数据集的分类结果图
1 Yan Jingwen, Chen Hongda, Liu Lei. Research Progress of Hyperspectral Image Classification[J]. Optical precision engineering,2019,27(3):175-188.
1 闫敬文,陈宏达,刘蕾.高光谱图像分类的研究进展[J].光学精密工程,2019,27(3):175-188.
2 Chen Y ,Lin Z , Zhao X , et al. Deep Learning-based Classification of Hyperspectral Data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6):2094-2107.
3 Zhang Haokui,Li Ying,Jiang Yenan. Research Status and Prospect of Deep Learning in Hyperspectral Image Classification[J]. Journal of Automation,2018,44(6):961-977.
3 张号逵,李映,姜晔楠.深度学习在高光谱图像分类领域的研究现状与展望[J].自动化学报,2018,44(6):961-977.
4 Wold S, Esbensen K, Geladi P. Principal Component Analysis[J]. Chemometrics & Intelligent Laboratory Systems, 1987,2(1):37-52.
5 Belhumeur P N, Hespanha J P, Kriegman D J. Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection[C]∥ European Conference on Computer Vision, 1996.
6 Ren Zhiwei, Wu Lingda. Feature Extraction Method of Hyperspectral Image based on Improved Principal Component Analysis of Information Quantity[J]. Journal of Armament Engineering,2018,39(7):151-154.
6 任智伟,吴玲达.基于信息量改进主成分分析的高光谱图像特征提取方法[J].兵器装备工程学报,2018,39(7):151-154.
7 Tadjudin S, Landgrebe D A. Robust Parameter Estimation for Mixture Model[J]. IEEE Transactions on Geoscience & Remote Sensing, 2000, 38(1):439-445.
8 Li Tie, Zhang Xinjun. The Application of Limit Learning Machine in Hyperspectral Remote Sensing Image Classification [J]. Optoelectronic Engineering,2016,43(11):62-68.
8 李铁, 张新君. 极限学习机在高光谱遥感图像分类中的应用[J]. 光电工程,2016,43(11):62-68.
9 Bioucas-Dias J M, Figueiredo M A T. Alternating Direction Algorithms for Constrained Sparse Regression: Application to Hyperspectral Unmixing[C]∥ 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. IEEE, 2010:1-4.
10 Shen Xiaozhong, Huang Yu, Su Weiwei, et al. Rapid Identification of Orange based on Hyperspectral Images[J]. Shizhen Guoyi Guoyao,2019,30(6):1391-1396.
10 沈小钟,黄宇,苏薇薇,等.基于高光谱图像的化橘红快速鉴别研究[J].时珍国医国药,2019,30(6):1391-1396.
11 Qi Yongfeng, Li Fayong. Hyperspectral Image Classification Algorithm based on Local Reserved Reduced Dimension Convolution Neural Network[J]. Journal of Agricultural Machinery,2019,50(3):136-143.
11 齐永锋,李发勇.基于局部保留降维卷积神经网络的高光谱图像分类算法[J].农业机械学报,2019,50(3):136-143.
12 Li W, Prasad S, Fowler J E, et al. Locality-preserving Dimensionality Reduction and Classification for Hyperspectral image Analysis[J]. IEEE Transactions on Geoscience and Remote Sensing,2011,50(4):1185-1198.
13 Zhou Y, Peng J, Chen C L P. Dimension Reduction Using Spatial and Spectral Regularized Local Discriminant Embedding for Hyperspectral Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2015,53(2):1082-1095.
14 Tang X, Han M. Partial Lanczos Extreme Learning Machine for Single-output Regression Problems[J]. Neurocomputing,2009,72(13-15):3066-3076.
15 Hu P, Wang L, Lu J G, et al. Improved Strategy of Genetic Algorithm for Optimum Location of Radio Frequency Identification Reader[J]. Sensor Letters,2012,10(8):1897-1901.
16 Yang J H, Wang L G, Qian J X. Hyperspectral Image Classification based on Spatial and Spectral Features and Sparse Representation[J]. Applied Geophysics,2014,11(4):489-499.
[1] 左成欢,赵辽英,陆海强,厉小润. 由粗到细的高光谱图像多端元光谱混合分析[J]. 遥感技术与应用, 2019, 34(6): 1305-1314.
[2] 牟多铎, 刘磊. ELM与SVM在高光谱遥感图像监督分类中的比较研究[J]. 遥感技术与应用, 2019, 34(1): 115-124.
[3] 刘爱林,郭宝平,李岩山 . 基于离散粒子群算法的凸多模态高光谱图像端元提取研究[J]. 遥感技术与应用, 2018, 33(2): 227-232.
[4] 苏阳,祁元,王建华,徐菲楠,张金龙. 基于航空高光谱影像的额济纳绿洲土地覆被提取[J]. 遥感技术与应用, 2018, 33(2): 202-211.
[5] 丁小辉,李华朋,张树清. 基于多态蚁群算法的高光谱遥感影像最优波段选择[J]. 遥感技术与应用, 2016, 31(2): 275-284.
[6] 张霞,孙伟超,帅通,孙艳丽. 基于小波变换的图像条带噪声去除方法[J]. 遥感技术与应用, 2015, 30(6): 1168-1175.
[7] 钱进,罗鼎. 基于成对约束半监督降维的高光谱遥感影像特征提取[J]. 遥感技术与应用, 2014, 29(4): 681-688.
[8] 袁宗泽,孙浩,计科峰,邹焕新. 基于Fisher字典学习稀疏表示的高光谱图像分类[J]. 遥感技术与应用, 2014, 29(4): 646-652.
[9] 吴樊,王超,张波,张红,田小娟. SAR图像船只分类识别研究进展[J]. 遥感技术与应用, 2014, 29(1): 1-8.
[10] 白黎娜, 王琫瑜, 田 昕, 卢 颖, 杨永恬. 基于多时相ENVISat ASAR数据的冬小麦识别方法—以北京通州试验区为例[J]. 遥感技术与应用, 2010, 25(4): 458-463.
[11] 张文杰,张钧萍,张晔. 基于区域活动轮廓模型的高光谱图像分割方法[J]. 遥感技术与应用, 2008, 23(3): 351-355.
[12] 况军, 罗建书, 向露. 基于自适应预测的高光谱遥感图像无损压缩算法[J]. 遥感技术与应用, 2007, 22(6): 739-742.
[13] 张 媛, 何明一, 梅少辉. 基于主分量和独立成分分析的多光谱目标检测[J]. 遥感技术与应用, 2006, 21(3): 227-231.
[14] 薛 绮, 匡纲要, 李智勇. 基于RM S 误差分析的高光谱图像自动端元提取算法[J]. 遥感技术与应用, 2005, 20(2): 278-283.
[15] 谷延锋,张 晔. 基于自动子空间划分的高光谱数据特征提取[J]. 遥感技术与应用, 2003, 18(6): 384-387.