吉林大学学报(地球科学版) ›› 2020, Vol. 50 ›› Issue (4): 1249-1260.doi: 10.13278/j.cnki.jjuese.20190133

• 地球探测与信息技术 • 上一篇    

引导滤波联合局部判别嵌入的高光谱影像分类

张辉1,2, 刘万军2, 吕欢欢2   

  1. 1. 辽宁工程技术大学电子与信息工程学院, 辽宁 葫芦岛 125105;
    2. 辽宁工程技术大学软件学院, 辽宁 葫芦岛 125105
  • 收稿日期:2019-06-28 发布日期:2020-07-29
  • 作者简介:张辉(1985-),男,博士研究生,主要从事高光谱影像处理技术研究,E-mail:zhjordan45@126.com
  • 基金资助:
    国家自然科学基金项目(41871379,61540056);辽宁省教育厅重点项目(LJ2017ZL003);辽宁省自然科学基金指导计划项目(20180550450)

Hyperspectral Image Classification Based on Guided Filtering Combined with Local Discrimination Embedding

Zhang Hui1,2, Liu Wanjun2, Lü Huanhuan2   

  1. 1. School of Electronic and Information Engineering, Liaoning Technique University, Huludao 125105, Liaoning, China;
    2. School of Software, Liaoning Technique University, Huludao 125105, Liaoning, China
  • Received:2019-06-28 Published:2020-07-29
  • Supported by:
    Supported by National Natural Science Foundation of China (41871379, 61540056), Key Project of Liaoning Provincial Education Department (LJ2017ZL003) and Liaoning Provincial Natural Science Fund Guidance Plan (20180550450)

摘要: 高光谱遥感影像分类是高光谱遥感影像处理和应用的重要组成部分。然而,高光谱遥感影像具有波段数量较多和空间分辨率较高等特点,给分类任务带来一定的挑战。为了提高分类精度,充分利用影像的空间信息和像素间的局部信息,提出一种引导滤波联合局部判别嵌入的高光谱影像分类方法。首先,对高光谱遥感影像进行归一化,利用主成分分析方法实现特征提取,将提取的第一主成分影像作为引导图像;其次,采用引导滤波分别提取各波段影像的空间特征;然后,将提取的空间影像特征进行叠加,通过局部Fisher判别分析完成低维嵌入;最后,将得到的低维嵌入特征输入支持向量机分类器得到分类结果。采用Indian Pines和Pavia University两幅高光谱影像进行实验的结果表明:在分别从各类地物中随机选取10%和100个样本作为训练样本的情况下,其总体分类精度分别提高到98.28%和99.45%;对比其他相关方法,该方法能够获取更高的分类精度。该方法在低维嵌入的同时,有效利用了影像的空间信息,改善了分类效果。

关键词: 高光谱影像分类, 引导滤波, 局部判别嵌入, 特征提取, 主成分分析

Abstract: Hyperspectral remote sensing image classification is an important part of hyperspectral remote sensing image processing and application. However, hyperspectral remote sensing image has the characteristics of large number of bands and high spatial resolution, which brings some challenges to image classification. To improve the classification accuracy of hyperspectral image and make full use of the spatial and local information, a classification method based on guided filtering combined with local discrimination embedding is proposed. Firstly, the hyperspectral remote sensing image is normalized, the feature extraction is realized by principal component analysis, and the extracted first principal component image is used as the guided image. Secondly, the spatial characteristics of each band are extracted by using the guided filter. Then, the extracted spatial image features are superimposed,and low-dimensional embedding is completed by local Fisher discriminant analysis. Finally, the embedded features are input into SVM to acquire classification results. The experimental results of two hyperspectral images, Indian Pines and Pavia University, show that compared to other relevant methods, the proposed method can obtain higher classification accuracy. When 10% and 100 samples from various ground objects were randomly selected as training samples, the overall classification accuracy increased to 98.28% and 99.45% respectively. At the same time of low dimensional embedding, the proposed method can effectively use the spatial information of images and improve the classification effect.

Key words: hyperspectral image classification, guided filtering, local discrimination embedding, feature extraction, principal component analysis

中图分类号: 

  • TP751
[1] 童庆禧,张兵,张立福.中国高光谱遥感的前沿进展[J]. 遥感学报,2016, 20(5):689-707. Tong Qingxi, Zhang Bing, Zhang Lifu. Current Progress of Hyperspectral Remote Sensing in China[J]. Journal of Remote Sensing, 2016, 20(5):689-707.
[2] Imani M. Manifold Structure Preservative for Hyperspectral Target Detection[J]. Advances in Space Research, 2018, 61(10):2510-2520.
[3] 杜培军,夏俊士,薛朝辉,等. 高光谱遥感影像分类研究进展[J]. 遥感学报,2016, 20(2):236-256. Du Peijun, Xia Junshi, Xue Zhaohui, et al. Review of Hyperspectral Remote Sensing Image Classification[J]. Journal of Remote Sensing, 2016, 20(2):236-256.
[4] Corson M R, Lucke R L, Davis C O, et al. The Hyperspectral Imager for the Coastal Ocean (HICOTM) Environmental Littoral Imaging from the International Space Station[J]. IEEE International Geoscience & Remote Sensing Symposium, 2010, 4(6):3752-3755.
[5] 蒋夕平,吴凤凰,蒋昱,等.基于FastICA算法的高光谱矿物丰度反演高光谱矿物填图应用[J]. 吉林大学学报(地球科学版),2013, 43(5):1681-1686. Jiang Xiping, Wu Fenghuang, Jiang Yu, et al. Hyper-Spectral Mineral Abundance Inversion Based on FastICA Algorithm[J]. Journal of Jilin University (Earth Science Edition), 2013, 43(5):1681-1686.
[6] Xie Weiying, Li Yunsong, Zhou Weiping. Feature Extraction of Hyperspectral Images with a Matting Model[J]. International Journal of Remote Sensing, 2018, 39(5):1510-1527.
[7] 叶涛,韦阿娟,黄志,等. 基于主成分分析法与Bayes判别法组合应用的火山岩岩性定量识别:以渤海海域中生界为例[J]. 吉林大学学报(地球科学版),2019, 49(3):873-880. Ye Tao, Wei Ajuan, Huang Zhi, et al. Quantitative Identification of Volcanic Lithology Based on Comprehensive Principal Component Analysis and Bayes Discriminant Method:A Case Study of Mesozoic in Bohai Bay[J]. Journal of Jilin University (Earth Science Edition), 2019, 49(3):873-880.
[8] Bandos T V, Bruzzone L, Camps-Valls G. Classification of Hyperspectral Images with Regularized Linear Discriminant Analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(3):862-873.
[9] He Xiaofei, Niyogi P. Locality Preserving Projections[M]. Cambridge:MIT Press, 2003.
[10] Sugiyama M. Dimensionality Reduction of Multimodal Labeled Data by Local Fisher Discriminant Analysis[J]. Journal of Machine Learning Research, 2007, 8(1):1027-1061.
[11] Wei L, 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, 2012, 50(4):1185-1198.
[12] 黄鸿,郑新磊. 高光谱影像空-谱协同嵌入的地物分类算法[J]. 测绘学报,2016, 45(8):964-972. Huang Hong, Zheng Xinlei. Hyperspectral Image Land Cover Classification Algorithm Based on Spatial-Spectral Coordination Embedding[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(8):964-972.
[13] 王俊淑,江南,张国明,等. 融合光谱-空间信息的高光谱遥感影像增量分类算法[J]. 测绘学报,2015, 44(9):1003-1013. Wang Junshu, Jiang Nan, Zhang Guoming, et al. Incremental Classification Algorithm of Hyperspectral Remote Sensing Images Based on Spectral-Spatial Information[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(9):1003-1013.
[14] Mirzapour F, Ghassemian H. Improving Hyperspectral Image Classification by Combining Spectral, Texture, and Shape Features[J]. International Journal of Remote Sensing, 2015, 36(4):1070-1096.
[15] 叶珍,白璘,粘永健. 基于Gabor特征与局部保护降维的高光谱图像分类算法[J]. 光学学报,2016, 36(10):512-521. Ye Zhen, Bai Lin, Nian Yongjian. Hyperspectral Image Classification Algorithm Based on Gabor Feature and Locality-Preserving Dimensionality Reduction[J]. Acta Optica Sinica, 2016, 36(10):512-521.
[16] 黄鸿,郑新磊,罗甫林. 基于Gabor特征与局部保护降维的高光谱图像分类算法[J]. 光子学报,2016,45(10):152-160. Huang Hong, Zheng Xinlei, Luo Fulin. Hyperspectral Image Classification with Combination of Weighted Mean Filter and Manifold Reconstruction Preserving Embedding[J]. Acta Photonica Sinica, 2016, 45(10):152-160.
[17] He K, Sun J, Tang X. Guided Image Filtering[J]. IEEE Transactions on Software Engineering, 2013, 35(6):1397-1409.
[18] Kumar P S, Supratim G, Sahu P K. Curvelet-Based Multiscale Denoising Using Non-Local Means & Guided Image Filter[J]. IET Image Processing, 2018, 12(6):909-918.
[19] 杨艳春,李娇,党建武,等. 基于引导滤波与改进PCNN的多聚焦图像融合算法[J]. 光学学报,2018, 38(5):86-95. Yang Yanchun, Li Jiao, Dang Jianwu, et al. Multi-Focus Image Fusion Based on Guided Filtering and Improved PCNN[J]. Acta Optica Sinica, 2018, 38(5):86-95.
[20] Pal M, Foody G M. Feature Selection for Classification of Hyperspectral Data by SVM[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(5):2297-2307.
[1] 白韬, 杨国东, 王凤艳, 刘佳为. 一种面向对象的最优分割尺度计算模型[J]. 吉林大学学报(地球科学版), 2020, 50(1): 304-312.
[2] 贺金鑫, 姜天, 董永胜, 韩凯旭, 马宁, 熊玥. 基于Landsat 8的辽宁弓长岭区遥感蚀变信息提取[J]. 吉林大学学报(地球科学版), 2019, 49(3): 893-901.
[3] 叶涛, 韦阿娟, 黄志, 赵志平, 肖述光. 基于主成分分析法与Bayes判别法组合应用的火山岩岩性定量识别:以渤海海域中生界为例[J]. 吉林大学学报(地球科学版), 2019, 49(3): 872-879.
[4] 韩启迪, 张小桐, 申维. 基于决策树特征提取的支持向量机在岩性分类中的应用[J]. 吉林大学学报(地球科学版), 2019, 49(2): 611-620.
[5] 束龙仓, 李姝蕾, 王松, 克热木·阿布都米吉提, 鲁程鹏, 李砚阁, 李伟. 岩溶水源地安全供水的风险评价指标筛选——以娘子关泉水源地为例[J]. 吉林大学学报(地球科学版), 2018, 48(3): 805-814.
[6] 陈盟, 吴勇, 高东东, 常鸣. 广汉市平原区浅层地下水化学演化及其控制因素[J]. 吉林大学学报(地球科学版), 2016, 46(3): 831-843.
[7] 于磊,邱殿明,刘莉,凌峰,李巍,胡广鑫,刘国才. 基于SPCA和AHP联合方法的滦河流域生态环境脆弱性变化规律分析[J]. 吉林大学学报(地球科学版), 2013, 43(5): 1588-1594.
[8] 陈圣波,刘彦丽,杨倩,周超,赵靓. 植被覆盖区卫星高光谱遥感岩性分类[J]. 吉林大学学报(地球科学版), 2012, 42(6): 1959-1965.
[9] 叶润青, 牛瑞卿, 张良培. 基于多尺度分割的岩石图像矿物特征提取及分析[J]. J4, 2011, 41(4): 1253-1261.
[10] 蒋立军, 邢立新, 梁一鸿, 潘军, 梁立恒, 黄竞铖. 融合化探信息的遥感异常提取[J]. J4, 2011, 41(3): 932-936.
[11] 张文, 陈剑平, 秦胜伍, 张晨, 李明, 马建全. 基于主成分分析的FCM法在泥石流分类中的应用[J]. J4, 2010, 40(2): 368-372.
[12] 陈永良, 林楠, 李学斌. 求解大样本核主成分分析模型的Lanczos算法[J]. J4, 2010, 40(1): 222-226.
[13] 辛 馨,杨俊鹏,赵奎涛,胡 克. 双台河口土壤中Mn、Zn和Rb的变化规律及其原因分析[J]. J4, 2007, 37(5): 983-0987.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!