基于多尺度空谱鉴别特征的高光谱图像分类

doi:10.11896／j.issn.1002-137X.2018.12.040

计算机科学 ›› 2018, Vol. 45 ›› Issue (12): 243-250.doi: 10.11896／j.issn.1002-137X.2018.12.040

基于多尺度空谱鉴别特征的高光谱图像分类

任守纲¹, 万升¹, 顾兴健¹, 王浩云¹, 袁培森¹, 徐焕良^1,2

(南京农业大学信息科技学院南京210095)¹
(国家信息农业工程技术中心南京210095)²

收稿日期:2018-03-01 出版日期:2018-12-15 发布日期:2019-02-25
作者简介:任守纲(1977-),男,博士,副教授,CCF会员,主要研究方向为图像处理、模式识别;万升(1993-),男,硕士,主要研究方向为机器学习、遥感影像处理;顾兴健(1985-),男,博士,讲师,CCF会员,主要研究方向为模式识别、机器学习;王浩云(1981-),男,博士,副教授,CCF会员,主要研究方向为高光谱检测、模式识别;袁培森(1980-),男,博士,讲师,CCF会员,主要研究方向为大数据分析与处理;徐焕良(1963-),博士,教授,CCF会员,主要研究方向为物联网工程,E-mail:huanliangxu@njau.edu.cn(通信作者)。
基金资助:
本文受国家自然科学基金(61502236),中央高校基本科研业务费专项(KYZ201753)资助

Hyperspectral Image Classification Based on Multi-scale Discriminative Spatial-spectral Features

REN Shou-gang¹, WAN Sheng¹, GU Xing-jian¹, WANG Hao-yun¹, YUAN Pei-sen¹, XU Huan-liang^1,2

(College of Information Science and Technology,Nanjing Agricultural University,Nanjing 210095,China)¹
(National Engineering and Technology Center for Infomation Agriculture,Nanjing 210095,China)²

Received:2018-03-01 Online:2018-12-15 Published:2019-02-25

摘要/Abstract

摘要： 为了应对高光谱图像同质区域面积分布不均的问题,同时更充分地挖掘空间和光谱信息之间的内在联系,提出了一种基于多尺度空谱鉴别特征的高光谱图像分类方法。该算法首先对图像进行不同尺度的滤波操作,接着分别从得到的多幅图像中提取鉴别的空谱特征,并使用支持向量机(SVM)进行分类。最后,该算法采取“决策级融合”的策略,来综合不同滤波尺度图像的分类结果。在Indian Pines,Kennedy Space Center和University of Pavia数据集上的实验表明,该算法能够提取较为有效的空间信息,当随机选取10%的像素作为训练样本时,该算法的总体分类准确率均能达到96%以上,其分类精度和Kappa系数均优于其他分类算法。

关键词: 地物分类, 多尺度, 高光谱图像, 空间信息

Abstract: In order to cope with the unevenness of homogenous regions’ area in hyperspectral images,an algorithm based on multi-scale discriminative spatial-spectral features was proposed.First,the image is processed with multi-scale filters.Then discriminative spatial-spectral information is extracted from the filtered images before put into SVM classifiers.At last,classification results of the filtered image are combined with decision fusion strategy.The experimental results on Indian Pines,Kennedy Space Center and University of Pavia indicate the effectiveness of the extracted spatial information.The overall accuracy of this algorithm can reach up to 96% when 10 percent of samples are randomly selected for training.What’s more,the classification accuracy and Kappa coefficient are higher than the comparative algorithms.

Key words: Hyperspectral images, Land cover classification, Multi-scale, Spatial information

中图分类号:

TP751.1

任守纲, 万升, 顾兴健, 王浩云, 袁培森, 徐焕良. 基于多尺度空谱鉴别特征的高光谱图像分类[J]. 计算机科学, 2018, 45(12): 243-250. https://doi.org/10.11896／j.issn.1002-137X.2018.12.040

REN Shou-gang, WAN Sheng, GU Xing-jian, WANG Hao-yun, YUAN Pei-sen, XU Huan-liang. Hyperspectral Image Classification Based on Multi-scale Discriminative Spatial-spectral Features[J]. Computer Science, 2018, 45(12): 243-250. https://doi.org/10.11896／j.issn.1002-137X.2018.12.040

参考文献

[1]MIYOSHI G T,IMAI N N,TOMMASELLI A M G,et al.Radiometric block adjustment of hyperspectral image blocks in the Brazilian environment[J].International Journal of Remote Sen-sing,2018,39(15-16):1-21.
[2]ZHANG Y X,GAO X Y,WANG T,et al.Background self-learning framework for bio information extraction from hyperp-sectral images [C]∥2014 academic annual meeting of Hubei Computer Society.2014:292-296.(in Chinese)
张玉香,高旭杨,王挺,等.一种基于背景自学习的高光谱图像生物信息提取方法[C]∥2014湖北省计算机学会学术年会.2014:292-296.
[3]WEN S X,LI S W,JIN X,et al.Research on Anthrax Disease Classification of Dangshan Pear Based on Hyperspectral Imaging Technology [J].Computer Science,2017,44(s1):216-219.(in Chinese)
温淑娴,李绍稳,金秀,等.基于高光谱的砀山酥梨炭疽病害等级分类研究[J].计算机科学,2017,44(s1):216-219.
[4]ZHANG X,PAN Z,LU X,et al.Hyperspectral image classification based on joint spectrum of spatial space and spectral space[J].Multimedia Tools & Applications,2018(3):1-19.
[5]LI D,CHENG Y,WANG X,et al.Incremental Graph Embedding Based on Spatial-Spectral Neighbors for Hyperspectral Ima-ge Classification[J].IEEE Access,2018,6(99):10996-11006.
[6]YANG L,WANG M,YANG S,et al.Hybrid ProbabilisticSparse Coding With Spatial Neighbor Tensor for Hyperspectral Imagery Classification[J].IEEE Transactions on Geoscience & Remote Sensing,2018,PP(99):1-12.
[7]ZHONG Z,LI J.Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification[OL].http://www.researchgate.net/publication/323076591_Generative_Adversarial_Networks_and_Probailistic_Graph_Models_for_Hyperspectral_Image_Classification.
[8]ZHANG B,LI S,JIA X,et al.Adaptive Markov Random Field Approach for Classification of Hyperspectral Imagery[J].IEEE Geoscience & Remote Sensing Letters,2011,8(5):973-977.
[9]LI W,PRASAD S,FOWLER J E.Hyperspectral Image Classification Using Gaussian Mixture Models and Markov Random Fields[J].Geoscience & Remote Sensing Letters IEEE,2014,11(1):153-157.
[10]LI J,BIOUCAS-DIAS J M,PLAZA A.Spectral-Spatial Hyperspectral Image Segmentation Using Subspace Multinomial Logistic Regression and Markov Random Fields[J].IEEE Transactions on Geoscience & Remote Sensing,2012,50(3):809-823.
[11]XIA J,CHANUSSOT J,DU P,et al.Spectral─Spatial Classification for Hyperspectral Data Using Rotation Forests With Local Feature Extraction and Markov Random Fields[J].IEEE Transactions on Geoscience & Remote Sensing,2015,53(5):2532-2546.
[12]IORDACHE M D,BIOUCAS-DIAS J M,PLAZA A.Total Varia-tion Spatial Regularization for Sparse Hyperspectral Unmixing[J].IEEE Transactions on Geoscience & Remote Sensing,2012,50(11):4484-4502.
[13]HUANG X,GUAN X,BENEDIKTSSON J A,et al.MultipleMorphological Profiles From Multicomponent-Base Images for Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2014,7(12):4653-4669.
[14]FU W,LI S,FANG L.Spectral-spatial hyperspectral image classification via superpixel merging and sparse representation[C]∥Geoscience and Remote Sensing Symposium.IEEE,2015:4971-4974.
[15]WANG J,JIAO L,LIU H,et al.Hyperspectral Image Classification by Spatial-Spectral Derivative-Aided Kernel Joint Sparse Representation[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2015,8(6):1-16.
[16]JI R,GAO Y,HONG R,et al.Spectral-Spatial Constraint Hyperspectral Image Classification[J].IEEE Transactions on Geoscience & Remote Sensing,2014,52(3):1811-1824.
[17]KANG X,LI S,BENEDIKTSSON J A.Spectral─Spatial Hyperspectral Image Classification With Edge-Preserving Filtering[J].IEEE Transactions on Geoscience & Remote Sensing,2014,52(5):2666-2677.
[18]TARABALKA Y,BENEDIKTSSON J A,CHANUSSOT J.Spectral-Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques[J].IEEE Transactions on Geoscience & Remote Sensing,2009,47(8):2973-2987.
[19]POMALAZA-RAEZ C,MCGILLEM C.An adaptative,nonli-near edge-preserving filter[J].IEEE Transactions on Signal Processing,1984,32(3):571-576.
[20]FAUVEL M,BENEDIKTSSON J A,CHANUSSOT J,et al.Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles[J].IEEE Transactions on Geoscience & Remote Sensing,2007,46(11):3804-3814.
[21]BAUER E,KOHAVI R.An Empirical Comparison of Voting Classification Algorithms:Bagging,Boosting,and Variants[J].Machine Learning,1999,36(1):105-139.
[22]JIMENEZ L O,MORALES-MORELL A,CREUS A.Classification of hyperdimensional data based on feature and decision fusion approaches using projection pursuit,majority voting,and neural networks[J].IEEE Transactions on Geoscience & Remote Sensing,1999,37(3):1360-1366.
[23]PAL M.Ensemble of support vector machines for land coverclassification[J].International Journal of Remote Sensing,2008,29(10):3043-3049.
[24]FAUVEL M,CHANUSSOT J,BENEDIKTSSON J A,et al.Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles[J].IEEE Transactions onGeo-science and Remote Sensing,2008,46(11):3804-3814.
[25]IMANI M,GHASSEMIAN H.Discriminant analysis in morphological feature space for high-dimensional image spatial-spectral classification[J].Journal of Applied Remote Sensing,2018,12(1):1.
[26]LI J,BIOUCAS-DIAS J M,PLAZA A.Semisupervised Hyperspectral Image Segmentation Using Multinomial Logistic Regression With Active Learning[J].IEEE Transactions on Geoscience & Remote Sensing,2010,48(11):4085-4098.
[27]SOOMRO B N,XIAO L,HUANG L,et al.Bilayer Elastic Net Regression Model for Supervised Spectral-Spatial Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2017,9(9):4102-4116.
[28]DIETTERICH T G.Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms[J].Neural Computation,1998,10(7):1895-1923.

相关文章 15

[1]	李瑶, 李涛, 李埼钒, 梁家瑞, Ibegbu Nnamdi JULIAN, 陈俊杰, 郭浩. 基于多尺度的稀疏脑功能超网络构建及多特征融合分类研究 Construction and Multi-feature Fusion Classification Research Based on Multi-scale Sparse Brain Functional Hyper-network 计算机科学, 2022, 49(8): 257-266. https://doi.org/10.11896/jsjkx.210600094
[2]	王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[3]	魏恺轩, 付莹. 基于重参数化多尺度融合网络的高效极暗光原始图像降噪 Re-parameterized Multi-scale Fusion Network for Efficient Extreme Low-light Raw Denoising 计算机科学, 2022, 49(8): 120-126. https://doi.org/10.11896/jsjkx.220200179
[4]	孙福权, 崔志清, 邹彭, 张琨. 基于多尺度特征的脑肿瘤分割算法 Brain Tumor Segmentation Algorithm Based on Multi-scale Features 计算机科学, 2022, 49(6A): 12-16. https://doi.org/10.11896/jsjkx.210700217
[5]	方连花, 林玉梅, 吴伟志. 随机多尺度序决策系统的最优尺度选择 Optimal Scale Selection in Random Multi-scale Ordered Decision Systems 计算机科学, 2022, 49(6): 172-179. https://doi.org/10.11896/jsjkx.220200067
[6]	范新南, 赵忠鑫, 严炜, 严锡君, 史朋飞. 结合注意力机制的多尺度特征融合图像去雾算法 Multi-scale Feature Fusion Image Dehazing Algorithm Combined with Attention Mechanism 计算机科学, 2022, 49(5): 50-57. https://doi.org/10.11896/jsjkx.210400093
[7]	张红民, 李萍萍, 房晓冰, 刘宏. 改进YOLOv3网络模型的人体异常行为检测方法 Human Abnormal Behavior Detection Method Based on Improved YOLOv3 Network Model 计算机科学, 2022, 49(4): 233-238. https://doi.org/10.11896/jsjkx.210300251
[8]	邵海琳, 季怡, 刘纯平, 徐云龙. 基于增强特征金字塔网络的场景文本检测算法 Scene Text Detection Algorithm Based on Enhanced Feature Pyramid Network 计算机科学, 2022, 49(2): 248-255. https://doi.org/10.11896/jsjkx.201100072
[9]	郑建炜, 黄娟娟, 秦梦洁, 徐宏辉, 刘志. 基于非局部相似及加权截断核范数的高光谱图像去噪 Hyperspectral Image Denoising Based on Non-local Similarity and Weighted-truncated NuclearNorm 计算机科学, 2021, 48(9): 160-167. https://doi.org/10.11896/jsjkx.200600135
[10]	陶星朋, 徐宏辉, 郑建炜, 陈婉君. 基于非凸低秩矩阵逼近和全变分正则化的高光谱图像去噪 Hyperspectral Image Denoising Based on Nonconvex Low Rank Matrix Approximation and TotalVariation Regularization 计算机科学, 2021, 48(8): 125-133. https://doi.org/10.11896/jsjkx.200400143
[11]	王栋, 周大可, 黄有达, 杨欣. 基于多尺度多粒度特征的行人重识别 Multi-scale Multi-granularity Feature for Pedestrian Re-identification 计算机科学, 2021, 48(7): 238-244. https://doi.org/10.11896/jsjkx.200600043
[12]	袁星星, 吴秦. 基于显著性特征和角度信息的遥感图像目标检测 Object Detection in Remote Sensing Images Based on Saliency Feature and Angle Information 计算机科学, 2021, 48(4): 174-179. https://doi.org/10.11896/jsjkx.191200027
[13]	巫勇, 刘永坚, 唐瑭, 王洪林, 郑建成. 基于鲁棒低秩张量恢复的高光谱图像去噪 Hyperspectral Image Denoising Based on Robust Low Rank Tensor Restoration 计算机科学, 2021, 48(11A): 303-307. https://doi.org/10.11896/jsjkx.210200103
[14]	顾兴健, 朱剑峰, 任守纲, 熊迎军, 徐焕良. 多尺度U网络实现番茄叶部病斑分割与识别 Multi-scale U Network Realizes Segmentation and Recognition of Tomato Leaf Disease 计算机科学, 2021, 48(11A): 360-366. https://doi.org/10.11896/jsjkx.201000166
[15]	朱戎, 叶宽, 杨博, 谢欢, 赵蕾. 基于改进DeeplabV3+的地物分类方法研究 Feature Classification Method Based on Improved DeeplabV3+ 计算机科学, 2021, 48(11A): 382-385. https://doi.org/10.11896/jsjkx.201100184

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于多尺度空谱鉴别特征的高光谱图像分类

Hyperspectral Image Classification Based on Multi-scale Discriminative Spatial-spectral Features

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0