[1]闫廷亚,王杉.夜间静止卫星红外云图的GHSOM网络云分类模型[J].江西师范大学学报(自然科学版),2015,(04):383-388.
 YAN Tingya,WANG Shan.The GHSOM Network Cloud Classification Model of Stationary Satellite Infrared Cloud Images at Night[J].Journal of Jiangxi Normal University:Natural Science Edition,2015,(04):383-388.
点击复制

夜间静止卫星红外云图的GHSOM网络云分类模型()
分享到:

《江西师范大学学报》(自然科学版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2015年04期
页码:
383-388
栏目:
出版日期:
2015-07-01

文章信息/Info

Title:
The GHSOM Network Cloud Classification Model of Stationary Satellite Infrared Cloud Images at Night
作者:
闫廷亚;王杉
华东交通大学信息工程学院,江西 南昌,330013
Author(s):
YAN Tingya;WANG Shan
关键词:
动态增长型分层自组织自组织映射夜间云图云分类
Keywords:
growing hierarchical self-organizing mapself-organizing feature mapnight cloud image:cloud classifi-cation
分类号:
TP183
文献标志码:
A
摘要:
针对夜间云分类准确率低下的问题,利用奇异值分解方法对FY-2E夜间红外云图进行特征提取和选择,从中筛选出包括亮温和分裂窗差值在内的不同的纹理特征。分别采用动态增长型分层自组织和自组织映射2种神经网络模型对夜间云图进行分类,并将2种网络模型的分类效果进行对比分析。实验结果表明:GHSOM网络模型在夜间云图分类方面效果较好,平均准确率总体上高于SOM,通过分层的分类方法极大地提高了夜间云图的分类准确率。
Abstract:
Aiming at the low accuracy of cloud classification at night,the features of FY-2E cloud images which in-clude bright temperatures and split window values were extracted and selected based on the method of singular value decomposition. The neural network models of growing hierarchical self-organizing map( GHSOM)and self-organi-zing map( SOM)were built separately to classify cloud images at night,meanwhile,contrasting the classified effect of the two network models. The experiments results showed that GHSOM network can improve the distinguishing effect of cloud images at night greatly through hierarchical classified method,and the average accuracy of cloud clas-sification results is higher than SOM.

参考文献/References:

[1] 吴咏明,张韧,蒋国荣,等.多光谱卫星图像的一种模糊聚类方法 [J].热带气象学报,2004,20(6):689-696.
[2] 张韧,王海俊,孙照渤,等.双光谱卫星云图的模糊推理云分类 [J].防灾减灾工程学报,2004,24(3):257-263.
[3] 陈晓颖,宋爱国,李建清,等.地基云图云状识别技术及其研究进展 [J].自动化技术与应用,2014,33(9):1-6.
[4] 尹跃.FY-2C资料对西北太平洋海域云分类的研究 [D].北京:北京大学,2008:1-5.
[5] Desbois M,Seze G,Szejwach G.Automatic classification of clouds on METEOSAT imagery [J].Journal of Applied Meteorogy,1981,3(21):401-412.
[6] Ameur Z,Ameur S,AdaneE A,et al.Cloud classication using the textural features of Meteosat images [J].Remote Sensing,2004,25(4):4491-4503.
[7] Berendes T,Mecikalski J,Mackenzie W,et al.Convective cloud identification and classification in daytime satellite imagery using standard deviation limited adaptive clustering [J].Journal of Geophysical Research,2008,113(20):1-9.
[8] Berendes T A,Kuo K S,Logar A,et al.A comparison of paired histogram,maximum likelihood,class elimination,and neural network approaches for daylight global cloud classification using AVHRR imagery [J].Journal of Geophysical Research,1999,104(D6):6199-6213.
[9] 黄招娣,应宛月,余立琴,等.基于PSO的神经网络优化证券投资组合方法研究 [J].华东交通大学学报,2013,30(2):42-46.
[10] Bankert R.Cloud classification of AVHRR imagery in maritime regions using a probabilistic neural network [J].Journal of Applied Meteorology,1994,33(8):909-918.
[11] Ahmed T.A system based on ratio images and quick probabilistic neural network for continuous cloud classification[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(12):1196-1203.
[12] 石小云.基于神经网络方法的卫星图像云分类[D].青岛:中国海洋大学,2012:50-52.
[13] Liu Yu,Xia Jun,Shi Chunxiang,et al.An improved cloud classification algorithm for China FY-2C multi-channel images using artificial neural network [J].Sensors,2009,9(7):5558-5579.
[14] Tian B,Shaikh M,Azimi-Sadjadi M,et al.A study of cloud classification with neural networks using spectral and textural features [J].IEEETransactions on Neural Networks,1999,10(1):138-151.
[15] Christodoulou C,Silas C,Constantinos S,et al.Multifeature texture analysis for the classification of clouds in satallite imagery [J].IEEE Transactions on Geosciences and Remote Sensing,2003,41(11):2662-2668.
[16] 王振,李朝锋,吴小俊.GHSOM在遥感图像分割中的应用 [J].计算机工程与应用,2010,46(16):188-190.
[17] 阳时来,杨雅辉,沈晴霓,等.一种基于半监督GHSOM的入侵检测方法 [J].计算机研究与发展,2013,50(11):2375-2382.
[18] 顾一鸣.基于自组织映射的故障诊断方法 [D].杭州:浙江大学,2006:24-28.
[19] 段文影,朱敏.基于粗糙集和自组织神经网络的聚类方法 [J].江西科学,2009,27(4):569-571.
[20] 李颖.基于神经网络的军事目标识别方法研究 [D].沈阳:沈阳理工大学,2005:10-25.
[21] 张利华,马均钊,勒国庆,等.基于BP神经网络的仓储烟草霉变预测 [J].华东交通大学学报,2013,30(3):71-75.
[22] 刘扬.基于静止气象卫星云图的分类研究 [D].青岛:中国海洋大学,2011:15-17.
[23] 郭胜,徐智勇.基于数字地球的3维云图实现技术 [J].首都师范大学学报:自然科学版,2013,34(2):70-73.
[24] 欧阳怡彪.空间数据挖掘的聚类方法与应用 [D].成都:电子科技大学,2006:59-76.
[25] 廖广兰,史铁林,刘世元,等.基于GHSOM网络的故障识别 [J].华中科技大学学报:自然科学版,2008,36(7):105-107.
[26] 刘强.人工神经网络方法在人脸检测和数据挖掘中的应用 [D].成都:电子科技大学,2005:55-65.

备注/Memo

备注/Memo:
国家自然科学基金(61261041)
更新日期/Last Update: 1900-01-01