采用多模糊支持向量机决策融合的积雨云检测

金炜; 符冉迪; 范亚会; 王文龙; 田文哲

doi:10.3788/OPE.20142212.3427

您当前的位置：

首页 >

文章列表页 >

采用多模糊支持向量机决策融合的积雨云检测

信息科学 | 更新时间：2020-08-13

- 采用多模糊支持向量机决策融合的积雨云检测
- Cumulonimbus detection by using decision fusion of multi-FSVM
- 光学精密工程 2014年22卷第12期页码：3427-3434
- 作者机构：
  
  宁波大学信息科学与工程学院,浙江宁波,315211
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.61271399,No.61373068)();宁波市自然科学基金资助项目(No.2011A610192,No.2013A610055)
- DOI：10.3788/OPE.20142212.3427
  中图分类号： TP751;P412.15
- 收稿日期：2014-08-25，
  
  修回日期：2014-10-16，
  
  纸质出版日期：2014-12-25
- 稿件说明：
移动端阅览
金炜, 符冉迪, 范亚会等. 采用多模糊支持向量机决策融合的积雨云检测[J]. 光学精密工程, 2014,22(12): 3427-3434

JIN Wei, Fu Ran-di, FAN Ya-hui etc. Cumulonimbus detection by using decision fusion of multi-FSVM[J]. Editorial Office of Optics and Precision Engineering, 2014,22(12): 3427-3434
金炜, 符冉迪, 范亚会等. 采用多模糊支持向量机决策融合的积雨云检测[J]. 光学精密工程, 2014,22(12): 3427-3434 DOI： 10.3788/OPE.20142212.3427.

JIN Wei, Fu Ran-di, FAN Ya-hui etc. Cumulonimbus detection by using decision fusion of multi-FSVM[J]. Editorial Office of Optics and Precision Engineering, 2014,22(12): 3427-3434 DOI： 10.3788/OPE.20142212.3427.

摘要

采用决策融合策略

提出了一种基于多模糊支持向量机(FSVM)的积雨云检测方法以解决添加更多的特征可增加云分类识别的准确率而特征维数过高又会造成过拟合现象的矛盾.该方法首先从训练云图提取光谱特征、通道亮温差特征、一阶灰度直方图纹理特征、灰度共生矩阵纹理特征以及Gabor小波特征

并组成包含5类特征的训练样本集;然后针对每类特征

训练5个FSVM子分类器.最后对各子分类器的结果在输出空间进行加权决策融合

以提高积雨云检测的准确率.实验结果表明

本文方法不仅较好地解决了积雨云检测中由于特征维数过高而造成的过拟合现象

而且能自适应地确定不同特征的权重

检测准确率优于各FSVM子分类器和包含所有输入特征的单FSVM分类器

有望在卫星云图分析中得到应用.

Abstract

A cumulonimbus detection approach was proposed based on Multi Fuzzy Support Vector Machine(FSVM) by using a decision fusion strategy to solve the contradiction that adding more features will increase the accuracy of cloud classification while cause over fitting phenomenon due to high feature dimensions. Firstly

spectral features

the brightness temperature difference of multi-channels

first order histogram texture features

gray level co-occurrence matrix texture features and Gabor wavelet features were extracted from training cloud images to form a training sample set which contains 5 kinds of features. Then

five FSVM sub-classifiers were trained respect to each kind of feature. Finally

the output of each sub-classifier was fused by weighted decision in the output space to improve the detection accuracy of the cumulonimbus. Experimental results show that the proposed approach solves the over fitting phenomenon in cumulonimbus detection caused by the too high feature dimensions and can determine the weight of different features adaptively. The results also demonstrate that the accuracy is not only superior to each FSVM sub-classifier but also to the FSVM classifier trained by all the input features at once. The proposed approach is expected to be applied in the analysis of satellite cloud images.

关键词

Keywords

references

LIU C C, SHYU T Y, CHAO C C,et al..Analysis on typhoon longwang intensity changes over the ocean via satellite data [J]. Journal of Marine Science and Technology, 2009,17:23-28.

THOMAS F, REMY R. An algorithm for the detection and tracking of tropical mesoscale convective systems using infrared images from geostationary satellite [J]. IEEE Transactions on Geoscience and Remote Sensing, 2013,51(7):4302-4315.

刘延安, 魏鸣, 高炜,等. FY-2 红外云图中强对流云团的短时自动预报算法[J]. 遥感学报, 2012, 16(1):86-92. LIU Y A,WEI M,GAO W,et al..Short-term automatic algorithm of severe convective cloud identification using FY-2 IR images[J].Journal of Remote Sensing,2012, 16(1):86-92.(in Chinese)

谭熊,余旭初,张鹏强,等. 基于多核支持向量机的高光谱影像非线性混合像元分解[J]. 光学精密工程,2014,22(7):1912-1920. TAN X,YU X CH,ZHANG P Q,et al..Norlinear mixed pixel decomposition of hyperspectral imagery based on multiple kernel[J].Opt. Precision Eng.,2014,22(7):1912-1920.(in Chinese)

周涛,陆惠玲,陈志强,等. 基于两阶段集成SVM的前列腺肿瘤识别[J]. 光学精密工程,2013,21(8):2137-2145. ZHOU T,LU H L,CHEN ZH Q,et al..Prostate tumor recognition based on two-stage intergrating SVM[J].Opt. Precision Eng.,2013,21(8):2137-2145.(in Chinese)

HONG G, HEYGSTER G, KUNZI K. Intercomparison of deep convective cloud fractions from passive infrared and microwave radiance measurements[J]. IEEE Trans. Geosci. Remote Sens., 2005, 2 (1) :18-22.

朱平,李生辰,王振会,等. 青藏高原东部暴雨云团局地强降水响应特征[J]. 遥感学报,2014,18(2):405-431. ZHU P,LI SH CH,WANG ZH H,et al..Characteristics of rainstorm cloud clusters to local heavy precipitation over the eastern Qinghai-Tibet plateau[J].Journal of Remote Sensing,2014,18(2):405-431.(in Chinese)

DING H, WEI Y, JIANG Q R, XIANBIN Z. Cloud type classification algorithm for CloudSat satellite based on support vector machine[J]. Transactions of Atmospheric Sciences, 2011,34:583-591.

MECIKALSKI J R, BEDKA K M. Forecasting convective initiation by monitoring the evolution of moving cumulus in daytime GOES imagery [J]. American Meteorological Society, 2006, 134(1):49-78.

THOMAS F, REMY R. Composite life cycle of tropical mesoscale convective systems from geostationary and low earth orbit satellite observations: method and sampling considerations [J]. Quarterly Journal of the Royal Meteorological Society, 2013,139(673):941-953.

凌剑勇, 何昕, 李一芒,等. 融合纹理特征与深度信息的足迹自动比对算法[J]. 光学精密工程, 2014,22(7):1946-1954. LING J Y,HE X,LI Y M,et al..Footprint automatic alignment algorithm fusing texture features and depth information[J].Opt. Precision Eng.,2014,22(7):1946-1954.(in Chinese)

王勇,杨公训,路迈西,等. 煤泥浮选泡沫图像灰度直方图及其统计纹理特征研究[J]. 选煤技术,2006,(1):13-16. WANG Y,YANG G X,LU M X,et al..Research on grey scale histogram of coal slime flotation froth image and its statistic texture characteristic [J].Coal Preparation Technology,2006,(1):13-16.(in Chinese)

HARALICK R M, SHANMUGAM K, DINSTEIN I. Textual features for image classification [J].IEEE Transactions on Systems Man and Cybernetics, 1973,3(6):610-621.

张刚,马宗民. 一种采用Gabor小波的纹理特征提取法[J]. 中国图像图形学报, 2010, 15(2):247-254. ZHANG G,MA Z M.Anapproach of using Gabor wavelets for texture feature extraction[J].Journal of Image and Graphics,2010, 15(2):247-254.(in Chinese)

刘三民,王彩霞,孙知信. 一种基于SVM后验概率的网络流量识别方法[J]. 计算机工程,2012,38(17):171-173. LIU S M,WANG C X,SUN ZH X.A network flow identification method based on SVM posterioi probability [J]. Compurter Engineering,2012,38(17):171-173.(in Chinese)

LOUISA L, SUEN C Y. Application of majority voting to pattern recognition:an analysis of its behavior and performance [J]. IEEE Trans. on Systems,Man,and Cybernetics, 1997,27(5):553-568.

浏览量

361

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

联合块匹配与稀疏表示的卫星云图修复