顾及局部与结构特征的稀疏多项式逻辑回归高光谱图像分类方法

doi:10.13474/j.cnki.11-2246.2019.0178

测绘通报 ›› 2019, Vol. 0 ›› Issue (6): 24-28.doi: 10.13474/j.cnki.11-2246.2019.0178

顾及局部与结构特征的稀疏多项式逻辑回归高光谱图像分类方法

沈宇臻¹, 官云兰², 杨禄³, 刘承承⁴, 严小芳⁵

1. 广州城市规划技术开发服务部, 广东广州 510030;
2. 东华理工大学测绘工程学院, 江西南昌 330013;
3. 桂林理工大学测绘地理信息学院, 广西桂林 541004;
4. 成都理工大学地球科学学院, 四川成都 610059;
5. 兴宁市国土资源局, 广东兴宁 514500

收稿日期:2018-11-29 出版日期:2019-06-25 发布日期:2019-07-01
通讯作者: 官云兰。E-mail:guan8098@163.com E-mail:guan8098@163.com
作者简介:沈宇臻(1995-),男,硕士,主要研究方向为遥感图像处理。E-mail:syzshx@163.com
基金资助:
国家自然科学基金（41401437）

Hyperspectral image classification based on local and structural feature with sparse multinomial logistic regression

SHEN Yuzhen¹, GUAN Yunlan², YANG Lu³, LIU Chengcheng⁴, YAN Xiaofang⁵

1. The Department of Guangzhou Urban Planning Technology Development Services, Guangzhou 510030, China;
2. Faculty of Geomatics, East China University of Technology, Nanchang 330013, China;
3. College of Geomatics and Geoinformation, GuiLin University of Technology, Guilin 541004, China;
4. College of Earth Science, Chengdu University of Technology, Chengdu 610059, China;
5. Xingning Municipal Bureau of Land and Resources, Xingning 514500, China

Received:2018-11-29 Online:2019-06-25 Published:2019-07-01

摘要/Abstract

摘要：

稀疏多项式逻辑回归在分类中仅利用图像光谱信息，导致分类效果不太理想。本文提出了一种顾及局部与结构特征的稀疏多项式逻辑回归高光谱图像分类方法。首先利用加权均值滤波与拓展形态学多属性剖面对原始高光谱图像进行局部与结构特征提取；然后对二者进行加权平均特征级融合以获取更具唯一性的像元特征；最后由稀疏多项式逻辑回归分类器对融合结果进行分类。结果表明，本文方法能有效地提高分类精度，而且具有较强的稳健性。

关键词: 高光谱影像, 特征融合, 加权均值滤波, EMAPs, 稀疏多项式逻辑回归

Abstract:

Sparse multinomial logistic regression only uses spectral information in image classification.Therefore,the classification effect is poor. In this paper,a hyperspectral image classification method based on local and structural feature with sparse multinomial logistic regression is proposed. Firstly, weighted mean filter and extended multi attribute profiles are used to extract local and structural features of the original hyperspectral images. Then the weighted average feature level fusion is carried out to obtain more unique pixel feat ures.Finally,the fusion results are classified by sparse multinomial logistic regression.The results show that the proposed method has well classification effect and robustness.

Key words: hyperspectral image, feature fusion, weighted mean filter, extended multi-attribute profiles, sparse multinomial logistic regression

中图分类号:

P237

沈宇臻, 官云兰, 杨禄, 刘承承, 严小芳. 顾及局部与结构特征的稀疏多项式逻辑回归高光谱图像分类方法[J]. 测绘通报, 2019, 0(6): 24-28.

SHEN Yuzhen, GUAN Yunlan, YANG Lu, LIU Chengcheng, YAN Xiaofang. Hyperspectral image classification based on local and structural feature with sparse multinomial logistic regression[J]. 测绘通报, 2019, 0(6): 24-28.

参考文献

[1] 孙艳丽.联合丰度信息与空谱特征的高光谱影像分类研究[D].北京:中国科学院遥感与数字地球研究所,2017.
[2] 孙乐.空谱联合先验的高光谱图像解混与分类方法[D].南京:南京理工大学,2014.
[3] 李彩虹,赵祎霏.一种高光谱图像的半监督分类方法[J].测绘通报,2018(2):46-49.
[4] 谷雨,徐英,郭宝峰.融合空谱特征和集成超限学习机的高光谱图像分类[J].测绘学报,2018,47(9):1238-1249.
[5] CAO Faxian, YANG Zhijing, REN Jinchang, et al. Extreme sparse multionmial logistic regression:a fast and roubust framework for hyperspectral image classification[J].Remote Sensing,2017,9(12):1255.
[6] KRISHNAPURAM B, CARIN L, FIGUEIREDO M A T, et al. Sparse multinomial logistic regression:fast algorithms and generalization bounds[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(6):957-968.
[7] BOHNING D. Multinomial logistic-regression algorithm[J].Annals of the Institute of Stati stical Mathematics,1992,44(1):197-200.
[8] ZHOU Yicong, PENG Jiangtao, 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.
[9] 鲍蕊.光谱和空间特征联合的高光谱遥感影像多分类器集成方法[D].南京:南京大学,2016.
[10] 王启聪.高光谱图像分类的GPU并行优化研究[D].南京:南京理工大学,2015.
[11] LI J, MARPU P R, PLAZA A, et al. Generalized composite kernelframework for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(9):4816-4829.
[12] LI J, HUANG X, GAMBA P, et al. Multiple feature learning for hyperspectral image classfication[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(3):1592-1606.
[13] LI J, BIOUCAS-DIAS J M, PLAZA A. Semisupervised hyperspectral image classification using soft sparse multinomial logistic regression[J].IEEE Geoscience Remote Sensing Letters,2013,10(2):318-322.
[14] BAO R, XIA J, MURA M D, et al. Combining morphological attribute profiles via an ensemble method for hyperspectral image classification[J]. IEEE Geoscience Remote Sensing Letters,2016,13(3):359-363.
[15] MURA M D, BENEDIKTSSON J A, WASKE B, et al. Morphological attribute profiles for the analysis of very high resolution images[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(10):3747-3762.

顾及局部与结构特征的稀疏多项式逻辑回归高光谱图像分类方法

Hyperspectral image classification based on local and structural feature with sparse multinomial logistic regression

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	窦世卿, 陈治宇, 徐勇, 郑贺刚, 苗林林, 宋莹莹. 基于多特征融合与典型降维方法的高光谱影像分类[J]. 测绘通报, 2022, 0(4): 32-36,50.
[2]	蔡怤晟, 向泽君, 蔡衡, 单德明. 结合特征选择的CVA多尺度遥感影像变化检测[J]. 测绘通报, 2020, 0(8): 101-104,130.
[3]	刘彦君, 张贵, 王潇, 周璀, 杨志高, 吴鑫, 张娟. 基于无人机高光谱影像波段选择的薇甘菊分类[J]. 测绘通报, 2020, 0(4): 34-39,52.
[4]	张鹏强, 刘冰, 余旭初, 谭熊, 杨帆, 周增华. 面向高光谱影像分类的生成式对抗网络[J]. 测绘通报, 2020, 0(3): 29-34.
[5]	周继苗, 李必军, 陈世增. 一种多层特征融合的道路场景实时分割方法[J]. 测绘通报, 2020, 0(1): 10-15.
[6]	刘相云, 龚志辉, 金飞, 杨光, 范炜康. 结合显著图和深度学习的遥感影像飞机目标识别[J]. 测绘通报, 2019, 0(3): 27-31.
[7]	周炜, 关洪军, 童俊. 一种利用高光谱像元分解技术提取水体边界的方法[J]. 测绘通报, 2019, 0(3): 120-123,140.
[8]	卢健, 马成贤, 周嫣然, 李哲. 双分支网络架构下的图像相似度学习[J]. 测绘通报, 2019, 0(12): 50-55.
[9]	李军胜, 党建武, 王阳萍. 多特征融合的高分辨率影像建筑物变化检测[J]. 测绘通报, 2019, 0(10): 105-108,118.
[10]	雒立群, 郭舟, 赵文智, 柴友玲, 张备, 董忠亮. 结合高光谱和高空间分辨率影像提取城市固体废弃物堆[J]. 测绘通报, 2016, 0(2): 38-41,78.
[11]	余旭初谭熊付琼莹王蔚涛. 联合纹理和光谱特征的高光谱影像多核分类方法[J]. 测绘通报, 2014, 0(9): 38-42.
[12]	杨可明钱小丽王林伟刘士文孙阳阳. 结合HSV和小波包变换的高光谱影像融合及信息识别研究[J]. 测绘通报, 2014, 0(5): 11-15.
[13]	张俪文汪云甲王行风. 仿射传播聚类在室内定位指纹库中的应用研究[J]. 测绘通报, 2014, 0(12): 36-39.