改进高斯过程回归的高光谱空谱联合分类算法

陈静; 张静

doi:10.3788/OPE.20192707.1649

您当前的位置：

首页 >

文章列表页 >

改进高斯过程回归的高光谱空谱联合分类算法

信息科学 | 更新时间：2020-08-13

- 改进高斯过程回归的高光谱空谱联合分类算法
- Spectral-spatial joint classification of hyperspectral image algorithm based on improved Gaussian process regression
- 光学精密工程 2019年27卷第7期页码：1649-1660
- 作者机构：
  
  1.广东工业大学华立学院，广东广州 511325
  2.西安科技大学测绘科学与技术学院，陕西西安 710054
  3.中国科学院南海海洋研究所广东省海洋遥感重点实验室, 广东广州 510301
- 作者简介：
  
  [ "陈静(1981-), 女, 汉族, 山东滕州人, 讲师, 2008年于辽宁工程技术大学获得硕士学位。主要研究方向：遥感图像处理与地理信息系统应用。E-mail:chenjing981@sina.com" ]
  [ "张静(1982-), 女, 汉族, 辽宁阜新人, 讲师, 2008年于辽宁工程技术大学获得硕士学位，2016年于长安大学获得博士学位。主要研究方向：测量数据处理与遥感技术。E-mail:zhangjingfly_82@sina.com" ]
- 基金信息：
  
  广东省海洋遥感重点实验室基金资助项目(2017B030301005-LORS1804);国家海洋局空间海洋遥感与应用研究重点实验室基金资助项目(201702002)
- DOI：10.3788/OPE.20192707.1649
  中图分类号： TP751, P237
- 收稿日期：2018-12-24，
  
  录用日期：2019-3-4，
  
  纸质出版日期：2019-07-15
- 稿件说明：
移动端阅览
陈静, 张静. 改进高斯过程回归的高光谱空谱联合分类算法[J]. 光学精密工程, 2019,27(7):1649-1660.

Jing CHEN, Jing ZHANG. Spectral-spatial joint classification of hyperspectral image algorithm based on improved Gaussian process regression[J]. Optics and precision engineering, 2019, 27(7): 1649-1660.
陈静, 张静. 改进高斯过程回归的高光谱空谱联合分类算法[J]. 光学精密工程, 2019,27(7):1649-1660. DOI： 10.3788/OPE.20192707.1649.

Jing CHEN, Jing ZHANG. Spectral-spatial joint classification of hyperspectral image algorithm based on improved Gaussian process regression[J]. Optics and precision engineering, 2019, 27(7): 1649-1660. DOI： 10.3788/OPE.20192707.1649.

摘要

针对高斯过程回归在高光谱图像分类中计算量较大、分类精度较低等问题，提出一种基于改进高斯过程回归的高光谱空谱联合分类算法。算法以最大方差为指标选取样本的子集缩小高斯过程回归参数求解的计算范围

采用平方根矩阵分解法对新添加样本进行模型结果预测，有效提升运算效率；算法以空间-光谱特征信息为基础，在像元近邻空间中重新定义邻域像元空-谱关联距离，将融入空间近邻信息的空-谱关联距离作为权值来度量邻域像元相似性，加大同类地物归为近邻的概率，从而提高地物分类的精度。在Indian Pines和Pavia University两组高光谱数据集上进行仿真实验，实验结果可知，与其他同类算法横向相比，本文提出的改进算法在总体分类精度、平均分类精度和Kappa系数等评价指标至少提高了2.3%，1.4%和1.07%，与改进前的模型算法纵向对比可知，本文提出的改进算法在取得较高总体分类精度的同时，大幅降低了算法的运行时间。

Abstract

To solve the problems of high calculation amounts and low classification accuracy of Gaussian process regression in hyperspectral image classification

a spectral-spatial joint classification algorithm for hyperspectral images based on improved Gaussian process regression was proposed. A subset of samples was selected using maximum variance as the index to narrow the calculation range of the Gaussian process regression parameter solution

and a square root matrix decomposition method was introduced to predict the model results for incoming added samples

all of which effectively improve the efficiency of calculation. A spatial-spectral correlation distance of neighborhood pixels was redefined in the pixel neighbor space based on spatial-spectral feature information. In addition

a space-spectrum correlation distance integrated with spatial neighbor information was used as the weight to measure the similarity of neighborhood pixels. These increase the probability that similar features would be classified as neighbors

thus improving the accuracy of feature classification. Simulation experiments were conducted on two sets of hyperspectral datasets from Indian Pines and Pavia University. Experimental results show that

compared with other similar algorithms

the proposed algorithm improves overall classification accuracy

average classification accuracy

and the Kappa coefficient by at least 2.3%

1.4%

and 1.07%

respectively. Compared with the model algorithm prior to enhancements

the improved algorithm not only achieves higher overall classification accuracy but also considerably reduces the running time.

关键词

Keywords

references

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 P J, XIA J S, XUE ZH H, et al .. Review of hyperspectral remote sensing image classification[J]. Journal of Remote Sensing, 2016, 20(2): 236-256. (in Chinese)

黄鸿, 陈美利, 段宇乐, 等.空-谱协同流形重构的高光谱影像分类[J].光学精密工程, 2018, 26(7): 1827-1836.

HUANG H, CHEN M L, DUAN Y L, et al .. Hyper-spectral image classification using spatial-spectral manifold reconstruction[J]. Opt. Precision Eng ., 2018, 26(7): 1827-1836. (in Chinese)

王庆超, 付光远, 汪洪桥, 等.多核融合多尺度特征的高光谱影像地物分类[J].光学精密工程, 2018, 26(4): 980-988.

WANG Q CH, FU G Y, WANG H Q, et al .. Fusion of multi-scale feature using multiple kernel learning for hyperspectral image land cover classification[J]. Opt. Precision Eng ., 2018, 26(4): 980-988. (in Chinese)

张春森, 郑艺惟, 黄小兵, 等.高光谱影像光谱-空间多特征加权概率融合分类[J].测绘学报, 2015, 44(8): 909-918.

ZHANG CH S, ZHENG Y W, HUANG X B, et al .. Hyperspectral image classification based on the weighted probabilistic fusion of multiple spectral-spatial features[J]. Acta Geodaetica Et Cartographica Sinica, 2015, 44(8): 909-918. (in Chinese)

孙乐, 吴泽彬, 冯灿, 等.一种新的两分类器融合的空谱联合高光谱分类方法[J].电子学报, 2015, 43(11): 2210-2217.

SUN L, WU Z B, FENG C, et al .. A novel two-classifier fusion method for spectral-spatial hyperspectral classification[J]. Acta Electronica Sinica , 2015, 43(11): 2210-2217. (in Chinese)

王彩玲, 王洪伟, 胡炳樑, 等.基于邻域分割的空谱联合稀疏表示高光谱图像分类技术研究[J]. 光谱学与光谱分析, 2016, 36(9): 2919-2924.

WANG C L, WANG H W, HU B L, et al .. A novel spatial-spectral sparse representation for hyperspectral image classification based on neighborhood segmentation[J]. Spectroscopy and Spectral Analysis, 2016, 36(9): 2919-2924. (in Chinese)

张成坤, 韩敏.基于边缘保持滤波的高光谱影像光谱-空间联合分类[J].自动化学报, 2018, 44(2): 280-288.

ZHANG CH K, HAN M. Spectral-spatial joint classification of hyperspectral image with edge-preserving filtering[J]. Acta Automatica Sinica , 2018, 44(2): 280-288. (in Chinese)

侯榜焕, 姚敏立, 贾维敏, 等.面向高光谱图像分类的空谱判别分析[J].光学精密工程, 2018, 26(2): 450-460.

HOU B H, YAO M L, JIA W M, et al .. Spatial-spectral discriminant analysis for hyperspectral image classification[J]. Opt. Precision Eng ., 2018, 26(2): 450-460. (in Chinese)

吕飞, 韩敏.基于深度极限学习机的高光谱遥感影像分类研究[J].大连理工大学学报, 2018, 58(2): 166-173.

LV F, HAN M. Hyperspectral remote sensing image classification based on deep extreme learning machine[J]. Journal of Dalian University of Technology , 2018, 58(2): 166-173. (in Chinese)

张康, 黑保琴, 周壮, 等.变异系数降维的CNN高光谱遥感图像分类[J].遥感学报, 2018, 22(1): 87-96.

ZHANG K, HEI B Q, ZHOU ZH, et al .. CNN with coefficient of variation-based dimensionality reduction for hyperspectral remote sensing images classification[J]. Journal of Remote Sensing , 2018, 22(1): 87-96. (in Chinese)

赵振凯, 杨明.结合分水岭分割的合成核SVM高光谱分类[J].数据采集与处理, 2018, 33(1): 132-143.

ZHAO ZH K, YANG M. Combining watershed segmentation with composite-kernels for hyperspectral image classification[J] . Journal of Data Acquisition and Processing, 2018, 33(1): 132-143. (in Chinese)

宋相法, 曹志伟, 郑逢斌, 等.基于随机子空间核极端学习机集成的高光谱遥感图像分类[J].计算机科学, 2016, 43(3): 301-304.

SONG X F, CAO Z W, ZHENG F B, et al .. Classification of hyperspectral remote sensing image based on random subspace and kernel extreme learning machine ensemble[J]. Computer Science , 2016, 43(3): 301-304. (in Chinese)

LIU Y, LI J, PLAZA A. Spectrometer-driven spectral partitioning for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2016, 9(2): 668-680.

YOUNES O, THOMAS N. A Path Connection Availability Model for MANETs with Random Waypoint Mobility [M]Computer Performance Engineering. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013: 111-126.

BARRETT J E, COOLEN A C C. Covariate dimension reduction for survival data via the Gaussian process latent variable model[J]. Statistics in Medicine, 2016, 35(8): 1340-1353.

SRIJITH P K, SHEVADE S. Gaussian Process Multi-Task Learning using Joint Feature Selection [M]Machine Learning and Knowledge Discovery in Databases. Berlin, Heidelberg: Springer Berlin Heidelberg, 2014: 98-113.

VERRELST J, ALONSO L, RIVERA CAICEDO J P, et al .. Gaussian process retrieval of chlorophyll content from imaging spectroscopy data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2013, 6(2): 867-874.

LAZARO-GREDILLA M, TITSIAS M K, VERRELST J, et al .. Retrieval of biophysical parameters with heteroscedastic Gaussian processes[J] . IEEE Geoscience and Remote Sensing Letters , 2014, 11(4): 838-842.

MURPHY R J, CHLINGARYAN A, MELKUMYAN A. Gaussian processes for estimating wavelength position of the ferric iron crystal field feature at ＄\sim＄900 nm from hyperspectral imagery acquired in the short-wave infrared (1002-1355 nm)[J]. IEEE Transactions on Geoscience and Remote Sensing , 2015, 53(4): 1907-1920.

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 H, ZHENG X L. Hyperspectral image land cover classification algorithm based on spatial-spectral coordination embedding[J]. Acta Geodaetica Et Cartographica Sinica, 2016, 45(8): 964-972. (in Chinese)

LI C H, KUO B C, LIN C T, et al .. A spatial-contextual support vector machine for remotely sensed image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(3): 784-799.

浏览量

162

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据