引用本文:	陈伟民,丁亚雄,宋冬梅,王斌,刘善伟,甄宗晋,张婷,杨敏.基于GA-WNN的极化SAR海洋溢油检测方法研究[J].海洋科学,2018,42(1):70-81.

【打印本页】【HTML】【下载PDF全文】【查看/发表评论】【下载PDF阅读器】【关闭】

过刊浏览高级检索

本文已被：浏览 1690次下载 975次	码上扫一扫！
分享到：微信更多字体:加大+\|默认\|缩小-
基于GA-WNN的极化SAR海洋溢油检测方法研究
陈伟民^1,2, 丁亚雄^1,2, 宋冬梅^1,3, 王斌^1,3, 刘善伟^1,3, 甄宗晋^1,2, 张婷⁴, 杨敏⁵
1.中国石油大学(华东) 地球科学与技术学院;2.中国石油大学(华东) 研究生院;3.海洋矿物资源实验室青岛海洋科学技术国家实验室;4.国家海洋局第一海洋研究所;5.国家海洋局北海分局

摘要:

海洋溢油对海洋生态和人类生活带来严重的影响。由于合成孔径雷达(Synthetic Aperture Radar,SAR)具有全天时全天候的工作能力, 在海洋溢油检测中发挥重要作用。目前, 极化SAR是SAR探测技术的先进手段。本文利用6个极化特征进行溢油检测, 通过对比分析这些特征对不同溢油的检测能力, 得出单一极化特征在溢油检测中存在不足。通过J-M特征优选方法, 提取出溢油检测识别度较高的特征影像, 并利用遗传算法优化的小波神经网络(Genetic Algorithm-Wavelet Neural Network,GA-WNN)进行溢油检测。利用2 套Radarsat-2全极化数据进行了方法验证, 结果表明, 该方法优于其他检测方法, 溢油检测精度分别达到90.31%和95.42%。

关键词: Radarsat-2 SAR 极化特征遗传算法小波神经网络海洋溢油

DOI：10.11759/hykx20171011001

分类号:

基金项目:国家重点研发计划(2017YFC1405600); 国家自然科学基金项目(41772350, 61371189, 41706208, 41701513)

Ocean oil-spill detection using Pol-SAR data based on GAWNN

CHEN Wei-min,DING Ya-xiong,SONG Dong-mei,WANG Bin,LIU Shan-wei,ZHEN Zong-jin,ZHANG Ting,YANG Min

Abstract:

Ocean oil spills seriously threaten both the marine environment and human activity. Synthetic aperture radar (SAR) plays an important role in ocean oil-spill detection due to its all-weather and day-and-night capabilities. Polarimetric SAR (Pol-SAR) is an advanced SAR detection technology that makes full use of the backscattering characteristics between SAR channels and has demonstrated obvious advantages in ocean oil-spill detection. We conducted experiments to investigate six polarimetric characteristics, based on the fact that a single characteristic can be inadequate in oil-spill detection with respect to the analysis of different features. Using the J-M distance index method to perform feature selection, we then used the genetic-algorithm-optimized wavelet neural network (GA-WNN) to detect oil spills. The experimental results from two sets of Radarsat-2 data confirm the superior accuracy of the proposed method with regard to oil-spill detection, i.e., 90.31% and 95.42%, espectively.

Key words: Radarsat-2 SAR Polarimetric SAR Characteristic Genetic Algorithm Wavelet Neural Network Ocean oil spill