紧缩极化SAR卷积神经网络溢油检测方法

doi:10.13474/j.cnki.11-2246.2024.0603

测绘通报 ›› 2024, Vol. 0 ›› Issue (6): 13-18.doi: 10.13474/j.cnki.11-2246.2024.0603

• 生态影响因子分析 • 上一篇

紧缩极化SAR卷积神经网络溢油检测方法

罗卿莉¹, 陈志远¹, 刘宇婷¹, 张进¹, 李煜²

1. 天津大学精密测试技术及仪器全国重点实验室, 天津 300072;
2. 北京工业大学, 北京 100036

收稿日期:2023-11-20 发布日期:2024-06-27
作者简介:罗卿莉(1985—),女,博士,副教授,主要研究方向为SAR遥感与INSAR应用。E-mail:luoqingli@tju.edu.cn
基金资助:
天津市轨道交通导航定位及时空大数据技术重点实验室开放课题基金(TKL2023B10);城市轨道交通数字化建设与测评技术国家工程实验室开放课题基金(2021ZH04);天津市自然科学基金重点项目(21JCZDJC00670);天津市交通运输科技发展计划(2022-40;2020-02);国家自然科学基金(41601446;41801284)

Oil spill detection method of compact polarization SAR based on convolution neural network

LUO Qingli¹, CHEN Zhiyuan¹, LIU Yuting¹, ZHANG Jin¹, LI Yu²

1. State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin 300072, China;
2. Beijing University of Technology, Beijing 100036, China

Received:2023-11-20 Published:2024-06-27

摘要/Abstract

摘要： 为研究利用紧缩极化SAR代替全极化SAR进行海洋溢油检测的可行性,以及不同极化参数对溢油检测准确率的影响,本文利用卷积神经网络(CNN)的SAR溢油检测算法,对全极化模式及由全极化构造的紧缩极化SAR数据分别提取极化参数,研究其对于溢油分类准确率的影响;同时对比不同SAR数据预处理步骤对溢油检测精度的影响。研究结果表明,对于预处理步骤,线性拉伸方法能够有效提升溢油检测的准确率;在极化参数选择上,极化参数极化熵H在全极化与紧缩极化模式上都取得最高的分类准确率,分别为0.972和0.978。该研究结果证明了利用紧缩极化SAR代替全极化SAR进行溢油检测的可行性,在溢油检测方面具有较好的应用潜力。

关键词: 海洋溢油, 合成孔径雷达, 紧缩极化, 极化分解, 卷积神经网络

Abstract: To investigate the feasibility of using compact polarimetric synthetic aperture radar (SAR) as an alternative to fully polarimetric SAR for oil spill detection and to determine the impact of different polarization parameters on the accuracy of oil spill detection. To this end,a SAR oil spill detection algorithm based on convolutional neural networks (CNN) is employed. This algorithm extracts polarization parameters from both fully polarimetric and derived compact polarimetric SAR data to study their impact on the classification accuracy of oil spills. Furthermore,the impact of different SAR data preprocessing steps on the accuracy of oil spill detection is evaluated. The results demonstrate that the linear stretching method can effectively enhance the accuracy of oil spill detection. Concerning the selection of polarization parameters,the polarization entropy H achieved the highest classification accuracy in both fully polarimetric and compact polarimetric modes,with a classification accuracy of 0.972 for fully polarimetric and 0.978 for compact polarimetric. This demonstrates the potential of using compact polarimetric SAR for oil spill detection and its promising application prospects.

Key words: marine oil spill, synthetic aperture radar, compact polarization, polarization decomposition, convolutional neural network

中图分类号:

P237

罗卿莉, 陈志远, 刘宇婷, 张进, 李煜. 紧缩极化SAR卷积神经网络溢油检测方法[J]. 测绘通报, 2024, 0(6): 13-18.

LUO Qingli, CHEN Zhiyuan, LIU Yuting, ZHANG Jin, LI Yu. Oil spill detection method of compact polarization SAR based on convolution neural network[J]. Bulletin of Surveying and Mapping, 2024, 0(6): 13-18.

参考文献

[1] DONG Y,LIU Y,HU C,et al.Chronic oiling in global oceans[J].Science,2022,376(6599):1300-1304.
[2] MA X,XU J,WU P,et al.Oil spill detection based on deep convolutional neural networks using polarimetric scattering information from Sentinel-1 SAR images[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-13.
[3] ROUSSO R,KATZ N,SHARON G,et al.Automatic recognition of oil spills using neural networks and classic image processing[J].Water,2022,14(7):1127.
[4] BASIT A,SIDDIQUE M A,BHATTI M K,et al.Comparison of CNNs and vision transformers-based hybrid models using gradient profile loss for classification of oil spills in SAR images[J].Remote Sensing,2022,14(9):2085.
[5] 李煜,陈杰,张渊智.合成孔径雷达海面溢油探测研究进展[J].电子与信息学报,2019,41(3):751-762.
[6] CLOUDE S R,POTTIER E.An entropy based classification scheme for land applications of polarimetric SAR[J].IEEE Transactions on Geoscience and Remote Sensing,1997,35(1):68-78.
[7] 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.
[8] ZHANG J,FENG H,LUO Q,et al.Oil spill detection in quad-polarimetric SAR images using an advanced convolutional neural network based on superpixel model[J].Remote Sensing,2020,12(6):944.
[9] ZHANG J,LUO Q,LI Y,et al.Oil spill detection using refined convolutional neural network based on quad-polarimetric SAR images[C]//Proceedings of the 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI).Changsha:IEEE,2019:528-536.
[10] SOUYRIS J C,IMBO P,FJORTOFT R,et al.Compact polarimetry based on symmetry properties of geophysical media:the /spl pi//4mode[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):634-646.
[11] COLLINS M J,DENBINA M,MINCHEW B,et al.On the use of simulated airborne compact polarimetric SAR for characterizing oil-water mixing of the deepwater horizon oil spill[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(3):1062-1077.
[12] WANG Xiaochen,SHAO Yun,ZHANG Fengli,et al.Comparison of C-and L-band simulated compact polarized SAR in oil spill detection[J].Frontiers of Earth Science,2019,13(2):351-360.
[13] ZHANG Y,LI Y,LIANG X,et al.Comparison of oil spill classifications using fully and compact polarimetric SAR images[J].Applied Sciences,2017,7(2):193.
[14] 舒思京,孟俊敏,张晰,等.基于简缩极化SAR的溢油检测与分类方法[J].海洋科学进展,2021,39(1):146-157.
[15] YIN J,YANG J,ZHOU L,et al.Oil spill discrimination by using general compact polarimetric SAR features[J].Remote Sensing,2020,12(3):479.

紧缩极化SAR卷积神经网络溢油检测方法

Oil spill detection method of compact polarization SAR based on convolution neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王淑香, 林雨准, 金飞, 杨小兵, 黄子恒, 程传祥. 结合融合策略的光学影像道路提取技术[J]. 测绘通报, 2024, 0(4): 6-12.
[2]	王东妍, 于才, 沈鹍, 张振见, 李亚峰. 点云数据在道岔关键节点几何检测应用[J]. 测绘通报, 2024, 0(3): 107-112.
[3]	高桂棠, 郗连霞, 钟晓龙. 基于卷积神经网络和无人机倾斜摄影图像的单个高层建筑物高度测算方法[J]. 测绘通报, 2024, 0(3): 118-122.
[4]	马锦山, 贾国焕, 张赛, 张炯. 基于多源高分辨率遥感影像的典型自然资源要素提取[J]. 测绘通报, 2024, 0(3): 123-126,150.
[5]	张萍, 李必军, 李垠, 张亦梅, 特木其勒, 刘可, 李治君. 面向震后快速灾害评估的遥感影像房屋数据空间化构建方法[J]. 测绘通报, 2024, 0(2): 69-73.
[6]	李冬瑞, 童鑫, 李文涛, 宋欣屿, 刘洁冰. 基于深度学习的卫星影像立体匹配算法[J]. 测绘通报, 2024, 0(1): 83-88.
[7]	李泽润, 喜文飞, 赵子龙, 刘海红, 张玉英, 张莉婷. SBAS-InSAR技术在昆明高铁南站山体形变监测中的应用[J]. 测绘通报, 2024, 0(1): 150-154.
[8]	王斌, 徐佳沅, 唐力明, 周立鹏. 小型斜坡隐患识别“空天地”图谱几何遥感方法[J]. 测绘通报, 2023, 0(8): 136-141.
[9]	王丽梅, 王延正. 基于高分辨率遥感影像的建筑物提取[J]. 测绘通报, 2023, 0(6): 180-183.
[10]	杜宇峰, 黄亮, 赵子龙, 李国柱. 基于DETR的高分辨率遥感影像滑坡体识别与检测[J]. 测绘通报, 2023, 0(5): 16-20.
[11]	齐建伟, 王伟峰, 张乐, 王光彦. 基于改进DeepLabV3+算法的遥感影像建筑物变化检测[J]. 测绘通报, 2023, 0(4): 145-149.
[12]	李子彧, 周维勋, 耿万轩. 联合类别筛选与重排序的交叉视角图像地理定位[J]. 测绘通报, 2023, 0(2): 40-45.
[13]	张永彬, 刘雅辉, 刘明月, 满卫东, 宋唐雷, 李春雨. 基于Relief F与卷积神经网络的湿地植物群落精细分类[J]. 测绘通报, 2023, 0(2): 58-64.
[14]	施仲添, 沈正伟, 杨四海. 基于前景感知的遥感影像建筑物提取方法[J]. 测绘通报, 2023, 0(2): 134-138.
[15]	齐杰, 王中辉, 李驿言. 基于图卷积神经网络的道路网匹配[J]. 测绘通报, 2023, 0(12): 19-24,44.