Please wait a minute...
img

官方微信

遥感技术与应用  2013, Vol. 28 Issue (1): 34-43    DOI: 10.11873/j.issn.1004-0323.2013.1.34
模型与反演     
SAR影像海洋表面溢油检测方法与实现
魏铼1,2,3,胡卓玮1,2,3
(1.首都师范大学资源环境与旅游学院,北京 100048;
2.资源环境与地理信息系统北京市重点实验室,北京 100048;
3.灾害评估与风险防范民政部重点实验室,北京 100048)
Method and Implementation of Oil Spill Detection in SAR Image
Wei Lai1,2,3,Hu Zhuowei1,2,3
(1.College of Resources Environment and Tourism,Capital Normal University,Beijing 100048,China;
2.Key Lab of Resources Environment and GIS,Beijing 100048 China;
3.Key Laboratory of Integrated Disaster Assessment and Risk Governance of the
Ministry of Civil Affairs,Beijing 100048,China)
 全文: PDF(4150 KB)  
摘要:

海洋是地球的重要组成部分,它为人类提供了丰富的物质和宝贵的资源,每年海洋都承受着不同程度的侵害,其中油类污染是给海洋造成巨大危害的污染之一。而油类污染又主要来源于轮船破裂漏油以及油井平台或海底输油管道爆炸等。每次事故造成的直接经济损失达几百万至上千万不等,所以对海上溢油进行监测具有重要的意义。选用Envisat的ASAR数据进行海上溢油检测,介绍并分析了SAR图像溢油检测的一般步骤及其实现方法,通过采用单一阈值分割法、最大熵分割法和非监督分类法对影像进行目标检测,从而粗略地将影像区分为前景区域与背景区域,并结合影像的纹理特征进行分类。在纹理特征选取过程中,通过人工选取部分溢油区与非溢油区作为感兴趣区,在感兴趣区上分别统计SAR影像常用的纹理特征,并结合不同目标检测的结果以及原始影像进行基于BP神经网络的分类,得到了良好的效果。最后展望了SAR图像海洋溢油检测的发展方向。

关键词: 海洋合成孔径雷达滤波增强型Lee溢油检测单一阈值最大熵非监督分类    
Abstract:

Ocean is one of the significant parts of the earth,which provides abundant resources for human beings.However,pollutions take place at different levels every year,in which oil pollution plays an important role.Oil pollution is mainly caused by oil leak from streamers and well platform,as well as by explosion of submarine pipe lines.Each accident may cost a direct economic losses ranging from millions to billions.Thus it is meaningful to develop oil spill monitoring.This paper uses a SAR data of Envisat monitoring marine oil spill,introduces and analyzes general steps and implementation of SAR images oil spill detection,chooses mean,variance,equivalent looks and speckle reduction capability as filtering effect evaluation indicators.Through these indicators,this study evaluates seven filters as follows,Lee,Enhanced Lee,Frost,Enhanced Frost,Gamma,Local sigma and Bit error,to compare,analyze and then draw a conclusion that enhanced Lee filter is the most appropriate for the images in the research.Then does target detection to images with single threshold segmentation,maximum entropy segmentation and unsupervised classification,thus divides image area to foreground region and background region roughly,at the same time,classifies by texture features of images.In the processes of texture features selection,this paper manually selects some oil spill areas and non-oil spill areas as regions of interest,and statistics of general texture features including mean,variance,homogeneity,contrast,dissimilarity,second moment and correlation of texture features of SAR images in regions of interest.The result indicates that mean,homogeneity,dissimilarity and second moment have the maximum differences between oil film and non-oil film,and these four texture feature parameters are selected and combined with results of targets detection and original images classification by BP neural network.The SAR data of Cosmo-Skymed with one meter resolution are used as basic data to verify the accuracy.Verification shows that the highest accuracy combined with maximum entropy is 86%.The second accuracy combined with single threshold is 81%~84%,the Isodata accuracy combined with unsupervised classification is 75%,the accuracy just combined with original images is 70%,the lowest accuracy without any targets detection is 57%.So targets detection plays a significant role in marine oil spill.This paper finally defines maximum entropy method as the best marine oil spill detecting method,and puts forward the direction of marine oil spill detection with SAR images in the end.

Key words: Ocean    SAR    Filter    Enhanced Lee    Oil spill detection    Single threshold    Maximum entropy    Unsupervised classification
收稿日期: 2012-01-16 出版日期: 2013-06-21
:  TP 79  
基金资助:

国家科技支撑计划项目课题(2012BAH33B03,2012BAH33B05,2008BAK49B07-2)。

通讯作者: 胡卓玮(1979-),男,江西乐平人,博士,副教授,主要从事灾害遥感与地理信息系统应用研究。Email:huzhuowei@gmail.com。   
作者简介: 魏铼(1989-),男,河南新密人,硕士研究生,主要从事海洋环境遥感与灾害遥感研究。Email:mitsubishisony@163.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
魏铼
胡卓玮

引用本文:

魏铼,胡卓玮. SAR影像海洋表面溢油检测方法与实现[J]. 遥感技术与应用, 2013, 28(1): 34-43.

Wei Lai,Hu Zhuowei. Method and Implementation of Oil Spill Detection in SAR Image. Remote Sensing Technology and Application, 2013, 28(1): 34-43.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2013.1.34        http://www.rsta.ac.cn/CN/Y2013/V28/I1/34

[1]Xue Haojie.Research on Oil Spill Detection Methods in SAR Images[D].Beijing:Institute of Electronics,Chinese Academy of Sciences,2004.[薛浩洁.SAR图像海洋表面油膜检测方法研究[D].北京:中国科学院电子学研究所,2004.]

[2]Xue Haojie,Chong Jinsong.Oil Spill Detection Methods in SAR Images[J].Remote Sensing Technology and Application,2004,19(4):290-294.[薛浩洁,种劲松.SAR图像海洋表面油膜检测方法[J].遥感技术与应用,2004,19(4):290-294.]

[3]Nunziata F,Gambardella A,Migliaccio M.Dual-Polarized Sar Data for Oil Spill Detection[C]// Proceedings of Envisat Symposium 2007,Montreux.Switzerland:European Space Agency,2007.

[4]Migliaccio M,Nunziata F,Gambardella A.On the Co-Polarized Phase Difference for Oil Spill Observation[J].International Journal of Remote Sensing,2009,30(6):1587-1602.

[5]Nunziata F,Gambardella A,Migliaccio M.On the Mueller Scattering Matrix for Sar Sea Oil Slick Observation[J].IEEE Geoscience and Remote Sensing Letters,2008,5(4):691-695.

[6]Benelli G.A Multi-resolution Approach to Oil-spills Detection in ERS-1 SAR Images[C]//Part of the EUROPTO Conference on Image and Signal Processing for Remote Sensing.Barcelona,Spain:European Space Agency,1998.

[7]Yu Wuyi,Li Jin,Shao Yun,et al.Remote Sensing Techniques for Oil Spill Monitoring in Offshore Oil and Gas Exploration and Exploitation Activities:Case Study in Bohai Bay[J].Petroleum Exploration and Development,2007,34(3):378-383.[于五一,李进,邵芸,等.海上油气勘探开发中的溢油遥感监测技术[J].石油勘探与开发,2007,34(3):378-383.]

[8]Xiong Wencheng,Wu Chuanqing,Wei Bin,et al.Oil Spill Detection with SAR in South Korea’s Oil Leak [J].Remote Sensing Technology and Application,2008,23(4):410-414.[熊文成,吴传庆,魏斌,等.SAR图像在韩国溢油监测中的应用[J].遥感技术与应用,2008,23(4):410-414.]

[9]Zou Yarong,Wang Hua,Zhu Haitian,et al.Study on Segmentation of SAR Image for Oil Spilled at Sea[J].Marine Environmental Science,2009,28(3):313-315.[邹亚荣,王华,朱海天,等.海上溢油SAR图像分割算法研究[J].海洋环境科学,2009,28(3):313-315.]

[10]Deng Lei.SAR Image Processing——Application on the Contoured Domain Hidden Markov Model[M].Beijing:Surveying and Mapping Press,2009.[邓磊.SAR图像处理方法——Contoured域隐马尔可夫模型的应用[M].北京:测绘出版社,2009.]

[11]Fortuny-Guasch J.Improved Oil Slick Detection and Classification with Polarimetric SAR[C]// Proceedings of the Workshop POLINSAR-Applications of SAR Polarimetry and Polarimetric Interferometry.Frascati,Italy:European Space Agency,2003.

[12]Mallat S.Characterization of Signal from Multiscale Edges[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(7):710-732.

[1] 杨军,裴剑杰. 一种改进的隐马尔可夫随机场遥感影像分割算法[J]. 遥感技术与应用, 2018, 33(5): 857-865.
[2] 张晓峰,吕晓琪,张信雪,张继凯,王月明,谷宇,樊宇. 多时刻海色遥感数据融合及其可视化[J]. 遥感技术与应用, 2018, 33(5): 873-880.
[3] 万玲,尤红建,程跃兵,卢晓军. 合成孔径雷达图像分割研究进展[J]. 遥感技术与应用, 2018, 33(1): 10-24.
[4] 熊伟,徐永力,姚力波,崔亚奇. 基于SVM的高分辨率SAR图像舰船目标检测算法[J]. 遥感技术与应用, 2018, 33(1): 119-127.
[5] 陈健,周杰,李雅雯. 基于静止卫星GOCI数据的陆地上空气溶胶光学厚度遥感反演[J]. 遥感技术与应用, 2017, 32(6): 1040-1047.
[6] 蒋松, 蓝爱兰,阎敬业,孙林. AgileDARN雷达数字信号处理的FPGA实现[J]. 遥感技术与应用, 2017, 32(6): 1064-1070.
[7] 王一明,蒙继华,程志强. 关键物候期遥感数据缺失条件下的数据同化研究[J]. 遥感技术与应用, 2017, 32(4): 615-623.
[8] 谢亚楠,周明亮,刘志坤. 合成孔径雷达反演降雨量算法的研究进展[J]. 遥感技术与应用, 2017, 32(4): 624-633.
[9] 李海英,温卫斌,王芳,付强,肖媛. 表层穿透雷达在月球与深空探测应用中的研究进展及趋势[J]. 遥感技术与应用, 2017, 32(4): 634-642.
[10] 陈坤堂,董晓龙,徐星欧,郎姝燕. 微波散射计反演海面风场的神经网络方法研究[J]. 遥感技术与应用, 2017, 32(4): 683-690.
[11] 姜萍,刘修国,陈启浩,邵芳芳. 利用多尺度SVM-CRF模型的极化SAR图像建筑物提取[J]. 遥感技术与应用, 2017, 32(3): 475-482.
[12] 张祥,陈报章,赵慧,汪磊. 基于时序Sentinel-1A数据的农田土壤水分变化检测分析[J]. 遥感技术与应用, 2017, 32(2): 338-345.
[13] 袁春琦,徐佳,程圆娥,陈媛媛,许康. 基于协同训练与集成学习的极化SAR图像半监督分类[J]. 遥感技术与应用, 2017, 32(2): 380-385.
[14] 孙景,唐丹玲,潘刚. Radarsat2全极化数据在监测南海溢油事件中的方法研究[J]. 遥感技术与应用, 2016, 31(6): 1181-1189.
[15] 张霞,戚文超,孙伟超. 基于数学形态滤波的植被光谱去噪方法研究[J]. 遥感技术与应用, 2016, 31(5): 846-854.