多模式融合下的海洋溢油高光谱成像油种识别方法

万剑华; 韩仲志; 宋欣欣; 刘杰

doi:10.3788/fgxb20163704.0473

您当前的位置：

首页 >

文章列表页 >

多模式融合下的海洋溢油高光谱成像油种识别方法

发光学应用及交叉前沿 | 更新时间：2020-08-12

- 多模式融合下的海洋溢油高光谱成像油种识别方法
- Oil Spills Identification Using Hyperspectral Imaging Based on Multi-pattern Method
- 发光学报 2016年37卷第4期页码：473-480
- 作者机构：
  
  1. 中国石油大学(华东) 地球科学学院,山东青岛,266580
  2. 青岛农业大学理学与信息科学学院,山东青岛,266109
  3. 青岛出入境检验检疫局,山东青岛,266001
- 作者简介：
- 基金信息：
  
  国家自然科学基金(31201133)();青岛市科技发展计划(14-2-3-52-nsh)资助项目()
- DOI：10.3788/fgxb20163704.0473
  中图分类号： O439
- 纸质出版日期：2016-4-5，
  
  收稿日期：2015-11-17，
  
  修回日期：2015-12-29，
扫描看全文
万剑华, 韩仲志, 宋欣欣等. 多模式融合下的海洋溢油高光谱成像油种识别方法[J]. 发光学报, 2016,37(4): 473-480

WAN Jian-hua, HAN Zhong-zhi, SONG Xin-xin etc. Oil Spills Identification Using Hyperspectral Imaging Based on Multi-pattern Method[J]. Chinese Journal of Luminescence, 2016,37(4): 473-480
万剑华, 韩仲志, 宋欣欣等. 多模式融合下的海洋溢油高光谱成像油种识别方法[J]. 发光学报, 2016,37(4): 473-480 DOI： 10.3788/fgxb20163704.0473.

WAN Jian-hua, HAN Zhong-zhi, SONG Xin-xin etc. Oil Spills Identification Using Hyperspectral Imaging Based on Multi-pattern Method[J]. Chinese Journal of Luminescence, 2016,37(4): 473-480 DOI： 10.3788/fgxb20163704.0473.

摘要

为利用不同油种的发光特性来探测海洋溢油

通过高光谱成像仪

在两种照明模式下采集了6种溢油油种的高光谱图像。基于33个波段构建了波段均值、波段差、波段比和归一化波段比4个辐射指数

提出了基于Fisher和PCA的模型共识的溢油高光谱特征选择方法

采用RBF-SVM模型对油种进行识别。比较发现

本文构建的基于光源混合、波段运算和模型共识的多模式融合方法

从不同侧面提高了模型的溢油识别能力

识别率达到了99.1%以上

比单一方法提高了10%以上。结果表明

多模式融合有效提高了海洋溢油的识别率。

Abstract

In order to identity different oil spill by the fluorescence phenomena of oil and its products

the hyperspectral images data of six varieties of oil spills samples were collected under two kind of illuminations (UV and halogen lights) using hyperspectral imaging camera. In the spectral region of 400-720 nm (10 nm spectral bandwidth)

four radiation index were obtained which include radiation index of individual spectral bands and the difference

ratio

and the normalized difference radiation index of consecutive spectral bands. Then

a novel method composed of Fisher and PCA to identify most significant wavelengths was proposed

and a classified model based on REF-SVM and the proposed method was established. By comparison

it is found that the different radiation index

light fusions and model consensus of feather selected method all can improve the accuracy of recognition rate. The overall accuracy rate by our method is above 99.1%

which is obviously higher than traditional methods only use one method. The experiment results show that the multi-pattern fusion can effectively improve the recognition rate of marine oil spill.

关键词

高光谱成像光源融合波段指数模型共识油种识别

Keywords

hyper-spectral imaginglight fusionsband indexmodel consensusoil identification

references

中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. GB/T 21247-2007 海面溢油鉴别系统规范 [S]. 北京: 中国标准出版社, 2008. General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China, China National Standardization Management Committee. GB/T 21247-2007 Specifications for Identification System of Spilled Oils on The Sea [S]. Beijing: China Standard Press, 2008. (in Chinese)

HAHN S, YOON G. Identification of pure component spectra by independent component analysis in glucose prediction based on mid-infrared spectroscopy [J]. Appl. Opt., 2006, 45(32):8374-8380.

WANG G Q, SUN Y A, DING Q Z, et al.. Estimation of source spectra profiles and simultaneous determination of poly component in mixtures from ultraviolet spectra data using kernel independent component analysis and support vector regression [J]. Anal. Chim. Acta, 2007, 594(1):101-106.

KIM M, LEE Y H, HAN C H. Real-time classification of petroleum products using near-infrared spectra [J]. Comput. Chem. Eng., 2000, 24(2-7):513-517.

王丽,卓林,何鹰,等. 近红外光谱技术鉴别海面溢油 [J]. 光谱学与光谱分析, 2004, 24(12):1537-1539. WANG L, ZHUO L, HE Y, et al.. Oil spill identification by near-infrared spectroscopy [J]. Spectrosc. Spect. Anal., 2004, 24(12):1537-1539. (in Chinese)

KESSLER J D, VALENTINE D L, REDMOND M C, et al.. A persistent oxygen anomaly reveals the fate of spilled methane in the deep Gulf of Mexico [J]. Science, 2011, 331(6015):312-315.

王春艳,史晓凤,李文东,等. 基于主成分和支持向量机浓度参量同步荧光光谱油种鉴别 [J]. 分析测试学报, 2014, 33(3):289-295. WANG C Y, SHI X F, LI W D, et al.. Concentration dependent synchronous fluorescence oil spill fingerprinting identification based on principal component analysis and support vector machine [J]. J. Instrum. Anal., 2014, 33(3):289-295. (in Chinese)

尹晓楠. 基于三维荧光光谱和小波分析的油品种类识别技术研究 [D]. 青岛: 中国海洋大学, 2012. YIN X N. Studies on The Identification of Oil Types Base on 3D Fluorescence Spectroscopy and Wavelet Analysis [D]. Qingdao: Ocean University of China, 2012. (in Chinese)

中华人民共和国交通运输部. JT/T 862-2013 水上溢油快速鉴别规程 [S]. 北京: 人民交通出版社, 2013. Ministry of Communications of the People's Republic of China. JT/T 862-2013 Oil Spill Identification Rules [S]. Beijing: China Communications Press, 2013. (in Chinese)

RAMSEY Ⅲ E, RANGOONWALA A, SUZUOKI Y, et al.. Oil detection in a coastal marsh with polarimetric synthetic aperture radar (SAR) [J]. Remote Sens., 2011, 3(12):2630-2662.

赵朝方,李晓龙,马佑军. 多通道海洋荧光激光雷达溢油监测系统 [J]. 红外与激光工程, 2011, 40(7):1263-1269. LI C F, LI X L, MA Y J. Multi-channel ocean fluorescence lidar system for oil spill monitoring [J]. Infrared Laser Eng., 2011, 40(7):1263-1269. (in Chinese)

JHA M N. Development of laser fluorosensor data processing system and GIS tools for oil spill response [EB/OL]. [2015-04-12]. http://www.geomatics.ucalgary.ca/research/publications.

王晶,刘湘南. 引入纹理特征的多光谱遥感影像海面油膜信息提取 [J]. 海洋通报, 2013, 32(4):452-459. WANG J, LIU X N. Oil spill information extraction based on textural features and multispectral image [J]. Mar. Sci. Bull., 2013, 32(4):452-459. (in Chinese)

韩仲志,万剑华,刘杰,等. 利用油品的紫外荧光特性的多光谱成像检测 [J]. 发光学报, 2015, 36(11): 1335-1341. HAN Z Z, WAN J H, LIU J, et al.. Multispectral imaging detection using the ultraviolet fluorescence characteristics of oil [J]. Chin. J. Lumin., 2015, 36(11):1335-1341. (in Chinese)

刘智深,丁宁,赵朝方,等. 主成分分析法在油荧光光谱波段选择中的应用 [J]. 地理空间信息, 2009, 7(3):12-15. LIU Z S, DING N, ZHAO C F, et al.. Application of the PCA method to band selection for oil fluorescence spectrums [J]. Geospat. Inform., 2009, 7(3):12-15. (in Chinese)

BACH F R, JORDAN M I. Kernel independent component analysis [J]. J. Mach. Learn. Res., 2003, 3:1-48.

CHANG C C, LIN C J. LIBSVM: a library for support vector machines [EB/OL]. (2011-9-30)[2015-04-12]. http://www.csie.ntu.edu.tw/-cjlin/libsvm.

DU B, ZHANG L P. Random-selection-based anomaly detector for hyperspectral imagery [J]. IEEE Trans. Geosci. Remote Sens., 2011, 49(5):1578-1589.

陈立旦,赵艳茹. 可见-近红外光谱联合随机蛙跳算法检测生物柴油含水量 [J]. 农业工程学报, 2014, 30(8): 168-173. CHEN L D, ZHAO Y R. Measurement of water content in biodiesel using visible and near infrared spectroscopy combined with Random-Frog algorithm [J]. Trans. Chin. Soc. Agric. Eng., 2014, 30(8):168-173. (in Chinese)

刘红玉,毛罕平,朱文静,等. 基于高光谱的番茄氮磷钾营养水平快速诊断 [J]. 农业工程学报, 2015, 31(S1):212-220. LIU H Y, MAO H P, ZHU W J, et al.. Rapid diagnosis of tomato N-P-K nutrition level based on hyperspectral technology [J]. Trans. Chin. Soc. Agric. Eng., 2015, 31(S1):212-220. (in Chinese)

艾施荣,吴瑞梅,吴彦红,等. 利用高光谱图像技术鉴别庐山云雾茶产地 [J]. 江西农业大学学报, 2014, 36(2):428-433. AI S R, WU R M, WU Y H, et al.. Identification of geographical origins of Lushan mist tea by hyper-spectral imaging technology [J]. Acta Agric. Univ. Jiangxiensis, 2014, 36(2):428-433. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于高光谱成像技术的长枣不同保藏温度的可溶性固形物含量检测方法

基于高光谱成像技术的脐橙叶片的叶绿素含量及其分布测量