Ship wake detection in SAR images with complex backgrounds based on relative total variation

doi:10.7523/j.issn.2095-6134.2017.06.010

Abstract

Abstract: The ship wake detection in SAR images is not only helpful in estimating the speeds and the directions of moving ships, but also in finding small ship objects. The existing ship wake detection methods achieve satisfactory results only for SAR images with simple backgrounds, but hardly work for SAR images with complex backgrounds. This work proposes a ship wake detection method for SAR images with complex backgrounds based on the relative total variation (RTV). The proposed method decomposes an SAR image into a cartoon component which contains ship wakes and an oscillating component which includes sea surface textures. Then the shearlet transform is used to process the cartoon component and some high-frequency coefficients are reconstructed to enhance the cartoon component. Finally the Radon transform is used for the enhanced cartoon component to detect ship wake lines. The comparison with the experimental results shows that the proposed method for the ship wake detection in SAR images with complex backgrounds obviously outperforms the existing methods.

Key words: synthetic aperture radar(SAR), ship wake detection, relative total variation(RTV), shearlet transform, Radon transform

CLC Number:

TP391

YANG Guozheng, YU Jing, SUN Weidong. Ship wake detection in SAR images with complex backgrounds based on relative total variation[J]. , 2017, 34(6): 734-742.

References

[1] Lyden J D, Hammond R R, Lyzenga D R, et al. Synthetic aperture radar imaging of surface ship wakes[J]. Journal of Geophysical Research:Oceans, 1988, 93(C10):12293-12303.
[2] Rey M T, Tunaley J K, Folinsbee J T, et al. Application of Radon transform techniques to wake detection in seasat-a SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(4):553-560.
[3] 种劲松, 朱敏慧. SAR图像舰船及其尾迹检测研究综述[J]. 电子学报, 2003, 31(9):1356-1360.
[4] Kuo J M, Chen K S. The application of wavelets correlator for ship wake detection in SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(6):1506-1511.
[5] Courmontagne P. An improvement of ship wake detection based on the radon transform[J]. Sig-nal Processing, 2005, 85(8):1634-1654.
[6] Xing X, Ji K, Zou H, et al. An enhancing normalized Radon transform method for ship wake detection in SAR imagery//Pro-ceedings of the 9th European Conference on Synthetic Aperture Radar:Frankfurt, Germany:VDE Press, 2012:559-562.
[7] 中国人民解放军第二炮兵装备研究院第三研究所. 一种海洋合成孔径雷达图像的舰船尾迹检测方法:中国, 2012100036752. 2012-07-04..http://epub.sipo.gov.cn/pam.action.
[8] 王世庆, 金亚秋. SAR图像船行尾迹检测的Radon变换和形态学图像处理技术[J]. 遥感学报, 2001, 5(4):289-294.
[9] Mata-Moya D, Jarabo-Amores P, Jimenez-Chaparro B, et al. Application of mean-shift fil-tering to ship wakes detection in SAR images//Proceedings of the 8th European Conference on Synthetic Aperture Radar:Frankfurt, Germany:VDE Press, 2010:1-4.
[10] 汤子跃, 朱敏慧, 王卫延. 一种SAR图象舰船尾迹的CFAR检测方法[J]. 电子学报, 2002, 30(9):1336-1339.
[11] Ai J, Qi X, Yu W, et al. A novel ship wake CFAR detection algorithm based on SCR en-hancement and normalized Hough transform[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(4):681-685.
[12] 种劲松, 朱敏慧. 基于归一化灰度Hough变换SAR图像舰船尾迹检测算法[J]. 中国图象图形学报, 2004, 9(2):146-150.
[13] Copeland A C, Ravichandran G, Trivedi M M. Localized Radon transform-based detection of ship wakes in SAR images[J]. IEEE Tran-sactions on Geoscience and Remote Sensing, 1995, 33(1):35-45.
[14] Aujol J F, Gilboa G, Chan T, et al. Struc-ture-texture image decomposition-modeling, al-gorithms, and parameter selection[J]. Inter-national Journal of Computer Vision, 2006, 67(1):111-136.
[15] 徐晨, 李敏, 张维强, 等. 后小波与变分理论及其在图像修复中的应用[M]. 北京:科学出版社, 2013.
[16] Xu L, Yan Q, Xia Y, et al. Structure extraction from texture via relative total variation[J]. ACM Transactions on Graphics, 2012, 31(6), Article 139:1-10.
[17] Kutyniok G, Labate D. Shearlets:Multiscale analysis for multivariate data[M]. Birkhäuser Boston:Springer press, 2012.
[18] Easley G, Labate D, Lim W Q. Sparse directional image representations using the discrete shearlet transform[J]. Applied and Computational Harmonic Analysis. 2008, 25(1):25-46.
[19] Agarwal S, Awan A, Roth D. Learning to detect objects in images via a sparse, part-based re-presentation[J]. IEEE Transaction on Pattern A-nalasis and Machine Intelligence. 2004, 26(11):1475-1490.