基于Faster R-CNN的卫星SAR图像南海海洋内波自动检测
Faster R-CNN based oceanic internal wave detection from SAR images in the South China Sea
- 2023年27卷第4期 页码：905-918
纸质出版日期： 2023-04-07
DOI： 10.11834/jrs.20211324
扫 描 看 全 文
浏览全部资源
扫码关注微信
摘要
海洋内波广泛存在于世界各大洋和边缘海中，在海洋能量串级中扮演着重要角色，在海洋资源开发、海洋工程建设和海洋军事活动等方面均具有重要学术价值与实际意义。海洋内波在合成孔径雷达SAR（Synthetic Aperture Radar）图像上呈现出亮暗相间的条纹状特征。本文利用2001年—2020年南海海域包含不同微波波段（C、L、X）、不同极化方式、不同空间分辨率的631幅星载SAR图像，构建了5480个SAR图像南海海洋内波样本，结合Faster R-CNN框架，利用迁移学习的方法，实现SAR图像上的海洋内波自动检测。模型识别准确率达到95.7%，召回率为92.3%，在准确率较高的同时还能保持较低的虚警率。该算法的建立使得基于海量卫星SAR数据检出海洋内波成为可能，从而为针对性地开展内波动力参数反演和过程研究提供了技术和数据基础。
Abstract
Oceanic internal waves are widely presented in all levels of the water column in deep oceans and marginal areas. These waves play an important role in seawater energy exchange. The study of oceanic internal waves has important academic values and practical significance in marine resources
marine engineering
and the marine military. The oceanic internal waves are distinct bright and dark stripes in Synthetic Aperture Radar (SAR) images. Those stripes can serve as clues to efficiently identify the oceanic internal waves from SAR images. The growing popularity of computer vision has led to the wide adoption of deep learning for the detection of oceanic features in remote sensing data. In this study
we intend to apply the faster R-CNN
a state-of-the-art deep learning method
to the automatic detection of oceanic internal waves.
The faster R-CNN is the most widely used version of the R-CNN family. This algorithm depends on the region proposal algorithms to hypothesize object locations. Based on the bright and dark stripes in the SAR images
a Faster R-CNN-based method is developed for oceanic internal wave detection. First
the oceanic internal waves are manually labeled in the SAR images to serve as the training set. The training set for the detection method contains 5480 SAR images
which are in multi-band
multi-polarization mode
and multi-spatial scale. These images are collected in the South China Sea region from 2001 to 2020. Then
the Faster R-CNN network is trained based on the obtained training set. Meanwhile
the parameters (such as training epochs) are optimized. The transfer learning technic is applied in the training process to transfer information from the previously learned tasks for detecting oceanic internal waves to accelerate the training process and avoid overfitting. The well-trained Faster R-CNN network can be applied by a sliding window on the SAR images to detect the oceanic internal waves. When the boundaries are obscured
the waves may be detected multiple times. In this case
the detection results will be grouped and merged. Finally
the detection results of the oceanic internal waves are acquired and recorded.
The evaluations are conducted on multi-source SAR data
showing that the accuracy rate (AP) and recall rate (AR) of the developed method are up to 95.7% and 92.3%
respectively. This method can achieve high accuracy while keeping the false alarm rate relatively low. The experiments on the SAR images with complex ocean conditions also show favorable results.
This work developed the approach for the detection of oceanic internal waves. This approach successfully transferred techniques developed in the computer vision field to solve the issues in remote sensing problems. The establishment of this method provides a technical basis for the detection of oceanic internal waves from a large amount of SAR data and further promotes the research of internal wave parameter inversion and dynamic processes. In addition
the proposed method was initially designed for lunar research
but it could be applied to the detection of other oceanic features.
关键词
海洋内波自动识别合成孔径雷达深度学习Faster R-CNN
Keywords
oceanic internal wavesautomatic detectionSAR imagesdeep learningFaster R-CNN
references
Ai J Q, Qi X Y and Yu W D. 2009. Improved two parameter CFAR ship detection algorithm in SAR images. Journal of Electronics and Information Technology, 31(12): 2881-2885
艾加秋, 齐向阳, 禹卫东. 2009. 改进的SAR图像双参数CFAR舰船检测算法. 电子与信息学报, 31(12): 2881-2885 [DOI: 10.3724/SP.J.1146.2008.01707http://dx.doi.org/10.3724/SP.J.1146.2008.01707]
Alpers W. 1985. Theory of radar imaging of internal waves. Nature, 314(6008): 245-247 [DOI: 10.1038/314245a0http://dx.doi.org/10.1038/314245a0]
Alpers W, He M X, Zeng K, Guo L F and Li X M. 2005. The distribution of internal waves in the East China Sea and the Yellow Sea studied by multi-sensor satellite images//Proceedings of 2005 IEEE International Geoscience and Remote Sensing Symposium. Seoul: IEEE: 4784-4787 [DOI: 10.1109/IGARSS.2005.1526742http://dx.doi.org/10.1109/IGARSS.2005.1526742]
Brandt P, Alpers W and Backhaus J O. 1996. Study of the generation and propagation of internal waves in the Strait of Gibraltar using a numerical model and synthetic aperture radar images of the European ERS 1 satellite. Journal of Geophysical Research, 101(C6): 14237-14252 [DOI: 10.1029/96JC00540http://dx.doi.org/10.1029/96JC00540]
Cai S Q and Gan Z J. 2001. Progress in the study of the internal solition in the northern South China Sea. Advances in Earth Science, 16(2): 215-219
蔡树群, 甘子钧. 2001. 南海北部孤立子内波的研究进展. 地球科学进展, 15(2): 215-219 [DOI: 10.3321/j.issn:1001-8166.2001.02.012http://dx.doi.org/10.3321/j.issn:1001-8166.2001.02.012]
Chen J, Chen B, Xu S Q. A Novel Method on Internal Wave Detection and Parameter Estimation from SAR Images. Journal of Image and Graphics, 2009, 14(1): 40-44
陈捷, 陈标, 许素芹. 2009. 一种新的SAR图像内波检测与参数估计方法. 中国图象图形学报, 2009, 14(1): 40-44 [DOI: 10.11834/jig.20090108http://dx.doi.org/10.11834/jig.20090108]
Da Silva J C B, Ermakov S A, Robinson I S, Jeans D R G and Kijashko S V. 1998. Role of surface films in ERS SAR signatures of internal waves on the shelf: 1. Short-period internal waves. Journal of Geophysical Research, 103(C4): 8009-8031 [DOI: 10.1029/97JC02725http://dx.doi.org/10.1029/97JC02725]
Ding C, Zhang B T, Gao G X, Chen B and Wu B Q. 2012. Feature detection of ocean internal wave in SAR image. Hydrographic Surveying and Charting, 32(5): 15-18
丁灿, 张本涛, 高国兴, 陈标, 吴宝勤. 2012. 合成孔径雷达图像中海洋内波的特征检测. 海洋测绘, 32(5): 15-18 [DOI: 10.3969/j.issn.1671-3044.2012.05.005http://dx.doi.org/10.3969/j.issn.1671-3044.2012.05.005]
Dong Y B, Zhang H, Wang C and Wang Y Y. 2019. Fine-grained ship classification based on deep residual learning for high-resolution SAR images. Remote Sensing Letters, 10(11): 1095-1104 [DOI: 10.1080/2150704X.2019.1650982http://dx.doi.org/10.1080/2150704X.2019.1650982]
Du T, Wu W and Fang X H. 2001. The generation and distribution of ocean internal waves. Marine Sciences, 25(4): 24-28
杜涛, 吴巍, 方欣华. 2001. 海洋内波的产生与分布. 海洋科学, 25(4): 24-28 [DOI: 10.3969/j.issn.1000-3096.2001.04.008http://dx.doi.org/10.3969/j.issn.1000-3096.2001.04.008]
Fang X H and Du T. 2005. Fundamentals of Oceanic Internal Waves and Internal Waves in the China Seas. Qingdao: China Ocean University Press: 1-15
方欣华, 杜涛. 2005. 海洋内波基础和中国海内波. 青岛: 中国海洋大学出版社: 1-15
Girshick R. 2015. Fast R-CNN//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago: IEEE: 1440-1448 [DOI: 10.1109/ICCV.2015.169http://dx.doi.org/10.1109/ICCV.2015.169]
Girshick R, Donahue J, Darrell T and Malik J. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE: 580-587 [DOI: 10.1109/cvpr.2014.81http://dx.doi.org/10.1109/cvpr.2014.81]
He K M, Xiang Y Z, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE: 770-778 [DOI: 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90]
Hinton G, Geoffrey E, Nitish S and Alex K. 2012. Improving neural networks by preventing co-adaptation of feature detectors. Computer Science, 3(4): 212-233 [DOI: 10.48550/arXiv.1207.0580http://dx.doi.org/10.48550/arXiv.1207.0580]
Hogan G G, Marsden J B and Henry J C. 2002. On the detection of internal waves in high resolution SAR imagery using the Hough transform//Proceedings of OCEANS 91 Proceedings. Honololu: IEEE: 1363-1369 [DOI: 10.1109/OCEANS.1991.606491http://dx.doi.org/10.1109/OCEANS.1991.606491]
Huang X D, Zhao H C, Zhao W, Zhang Z W, Zhou C, Yang Q X and Tian J W. 2016. An extreme internal solitary wave event observed in the northern South China Sea. Scientific Reports, 6(1): 30041 [DOI: 10.1038/srep30041http://dx.doi.org/10.1038/srep30041]
Jia T, Liang J J, Li X M and Sha J. 2018. SAR observation and numerical simulation of internal solitary wave refraction and reconnection behind the Dongsha atoll. Journal of Geophysical Research, 123(1): 74-89 [DOI: 10.1002/2017JC013389http://dx.doi.org/10.1002/2017JC013389]
Jiang G R, Wang X J, Zhang J and Zhang R. 2005. The development of internal waves research at home and abroad. Marine Forecasts, 22(S1): 176-182
蒋国荣, 汪晓娇, 张军, 张韧. 2005. 内波研究的国内外发展现状. 海洋预报, 22(S1): 176-182 [DOI: 10.3969/j.issn.1003-0239.2005.z1.026http://dx.doi.org/10.3969/j.issn.1003-0239.2005.z1.026]
Kang J, Zhang J, Song P J and Meng J M. 2008. The application of two-dimensional EMD to extracting internal waves in SAR images//Proceedings of 2008 International Conference on Computer Science and Software Engineering. Wuhan: IEEE: 953-956 [DOI: 10.1109/CSSE.2008.1224http://dx.doi.org/10.1109/CSSE.2008.1224]
Li X M, Huang B Q, Jia T and Qin T T. 2020. Ocean remote sensing by spaceborne synthetic aperture radar (SAR) and big data. Journal of Nanjing University of Information Science and Technology (Natural Science Edition), 12(2): 191-203
李晓明, 黄冰清, 贾童, 覃婷婷. 2020. 星载合成孔径雷达海洋遥感与大数据. 南京信息工程大学学报(自然科学版), 12(2): 191-203 [DOI: 10.13878/j.cnki.jnuist.2020.02.006http://dx.doi.org/10.13878/j.cnki.jnuist.2020.02.006]
Li Z L, Wang L Y, Jiang S, Wu Y H and Zhang Q J. 2021. On orbit extraction method of ship target in SAR images based on ultra-lightweight network. Journal of Remote Sensing, 25(3): 765-775
李宗凌, 汪路元, 蒋帅, 吴雨航, 张庆君. 2021. 超轻量网络的SAR图像舰船目标在轨提取. 遥感学报, 25(3): 765-775 [DOI: 10.11834/jrs.20210160http://dx.doi.org/10.11834/jrs.20210160]
Lin H, Fan K G, Shen H, Huang W G and He M X. 2010. Review on remote sensing of oceanic internal wave by space-borne SAR. Progress in Geophysics, 25(3): 1081-1091
林珲, 范开国, 申辉, 黄韦艮, 贺明霞. 2010. 星载SAR海洋内波遥感研究进展. 地球物理学进展, 25(3): 1081-1091 [DOI: 10.3969/j.issn.1004-2903.2010.03.049http://dx.doi.org/10.3969/j.issn.1004-2903.2010.03.049]
Liu C X, Ji Y L and Hu X F. 2005. Research status and perspective of internal tide and internal wave deposits. Marine Geology Frontiers, 21(3): 6-11
刘成鑫, 纪友亮, 胡喜锋. 内潮汐和内波沉积研究现状与展望. 海洋地质动态, 2005, 21(3): 6-11 [DOI: 10.3969/j.issn.1009-2722.2005.03.002http://dx.doi.org/10.3969/j.issn.1009-2722.2005.03.002]
Marghany M. 1999. Internal wave detection and wavelength estimation//Proceedings of IEEE 1999 International Geoscience and Remote Sensing Symposium. Hamburg: IEEE: 163-165 [DOI: 10.1109/IGARSS.1999.773434http://dx.doi.org/10.1109/IGARSS.1999.773434]
Rambour C, Audebert N, Koeniguer E, Le Saux B, Crucianu1 M and Datcu M. 2020. Flood detection in time series of optical and SAR images. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 43(B2): 1343-1346 [DOI: 10.5194/isprs-archives-XLIII-B2-2020-1343-2020http://dx.doi.org/10.5194/isprs-archives-XLIII-B2-2020-1343-2020]
Ren S Q, He K M, Girshick R and Sun J. 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6): 1137-1149 [DOI: 10.1109/TPAMI.2016.2577031http://dx.doi.org/10.1109/TPAMI.2016.2577031]
Rodenas J A and Garello R. 1997. Wavelet analysis in SAR ocean image profiles for internal wave detection and wavelength estimation. IEEE Transactions on Geoscience and Remote Sensing, 35(4): 933-945 [DOI: 10.1109/36.602535http://dx.doi.org/10.1109/36.602535]
Rodenas J A and Garello R. 1998. Internal wave detection and location in SAR images using wavelet transform. IEEE Transactions on Geoscience and Remote Sensing, 36(5): 1494-1507 [DOI: 10.1109/36.718853http://dx.doi.org/10.1109/36.718853]
Salamon J and Bello J P. 2017. Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Processing Letters, 24(3): 279-283 [DOI: 10.1109/LSP.2017.2657381http://dx.doi.org/10.1109/LSP.2017.2657381]
Simonyan K and Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. [DOI: 10.48550/arXiv.1409.1556http://dx.doi.org/10.48550/arXiv.1409.1556]
Takahashi N, Gygli M, Pfister B and van Gool L. 2016. Deep convolutional neural networks and data augmentation for acoustic event detection. [DOI: 10.48550/arXiv.1604.07160http://dx.doi.org/10.48550/arXiv.1604.07160]
Xu J F, Zhang B Mg, Yu D H, Lin Y Z and Guo H T. 2020. Aircraft target change detection for high-resolution remote sensing images using multi-feature fusion. Journal of Remote Sensing, 24(1): 37-52
徐俊峰, 张保明, 余东行, 林雨准, 郭海涛. 2020. 多特征融合的高分辨率遥感影像飞机目标变化检测. 遥感学报, 24(1): 37-52 [DOI: 10.11834/jrs.20208213http://dx.doi.org/10.11834/jrs.20208213]
Xu T T. 1999. Ocean Internal Wave Dynamics. Beijing: Science Press
徐肇廷. 1999. 海洋内波动力学. 北京: 科学出版社
Yang J S. 2005. Synthetic Aperture Radar Sea Surface Wind Field. Ocean Wave and Internal Wave Remote Sensing Technology. Beijing: Ocean Press
杨劲松. 2005. 合成孔径雷达海面风场、海浪和内波遥感技术. 北京: 海洋出版社
Zheng Y G, Zhang H S, Li X L and Zhang Z H. 2020. Detection algorithm of internal waves in the South China Sea based on boundary characteristics of remote sensing image. Journal of Tropical Oceanography, 39(6): 41-56
郑应刚, 张洪生, 李晓恋, 张周昊. 2020. 基于遥感影像边界特性对南海海洋内波检测算法研究. 热带海洋学报, 39(6): 41-56 [DOI: 10.11978/2019120http://dx.doi.org/10.11978/2019120]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
北京林业大学 信息学院
国家林业和草原局林业智能信息处理工程技术研究中心
南京信息工程大学 遥感与测绘工程学院
北京师范大学 遥感科学国家重点实验室
武汉大学 测绘遥感信息工程国家重点实验室
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部