Précédent|Prochain

Faster R-CNN based oceanic internal wave detection from SAR images in the South China Sea

  • role： First author第一作者
  • Affiliation：

    Hainan Key Laboratory of Earth Observation,Hainan Aerospace Information Research Institute, Chinese Academy of Sciences, Sanya 572029, China

    College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, China

  • Email：Hongliang_sun@glut.edu.cn
  • Introduction：孙宏亮，研究方向为卫星海洋遥感。E-mail： Hongliang_sun@glut.edu.cn
SUN Hongliang12,  
  • Affiliation：

    Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

WANG Yiran3,  
  • Affiliation：

    Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

    University of Chinese Academy of Sciences, Beijing 100049, China

JIA Tong34,  
  • Affiliation：

    61741 Troops, Beijing 100094, China

SHI Yingni5,  
  • role： Corresponding author通信作者
  • Affiliation：

    Hainan Key Laboratory of Earth Observation,Hainan Aerospace Information Research Institute, Chinese Academy of Sciences, Sanya 572029, China

    Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

  • Email：lixiaoming@aircas.ac.cn
  • Introduction：李晓明，研究方向为卫星海洋遥感。E-mail： lixiaoming@aircas.ac.cn
LI Xiaoming13*

résumé

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.

mots-clés

oceanic internal waves;automatic detection;SAR images;deep learning;Faster R-CNN

References

  1. 1.
    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
  2. 2.
    Alpers W. 1985. Theory of radar imaging of internal waves. Nature, 314(6008): 245-247
  3. 3.
    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
  4. 4.
    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
  5. 5.
    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
  6. 6.
    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
  7. 7.
    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
  8. 8.
    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
  9. 9.
    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
  10. 10.
    Du T, Wu W and Fang X H. 2001. The generation and distribution of ocean internal waves. Marine Sciences, 25(4): 24-28
  11. 11.
    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
  12. 12.
    Girshick R. 2015. Fast R-CNN//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago: IEEE: 1440-1448
  13. 13.
    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
  14. 14.
    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
  15. 15.
    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
  16. 16.
    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
  17. 17.
    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
  18. 18.
    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
  19. 19.
    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
  20. 20.
    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
  21. 21.
    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
  22. 22.
    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
  23. 23.
    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
  24. 24.
    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
  25. 25.
    Marghany M. 1999. Internal wave detection and wavelength estimation//Proceedings of IEEE 1999 International Geoscience and Remote Sensing Symposium. Hamburg: IEEE: 163-165
  26. 26.
    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
  27. 27.
    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
  28. 28.
    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
  29. 29.
    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
  30. 30.
    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
  31. 31.
    Simonyan K and Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition.
  32. 32.
    Takahashi N, Gygli M, Pfister B and van Gool L. 2016. Deep convolutional neural networks and data augmentation for acoustic event detection.
  33. 33.
    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
  34. 34.
    Xu T T. 1999. Ocean Internal Wave Dynamics. Beijing: Science Press
  35. 35.
    Yang J S. 2005. Synthetic Aperture Radar Sea Surface Wind Field. Ocean Wave and Internal Wave Remote Sensing Technology. Beijing: Ocean Press
  36. 36.
    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

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website