专题论文

Sentinel-1双极化数据舰船目标几何特性提取

  • 李博颖 ,
  • 柳彬 ,
  • 郭炜炜 ,
  • 张增辉 ,
  • 郁文贤
展开
  • 上海交通大学智能探测与识别上海市重点实验室, 上海 200240
李博颖,博士研究生,研究方向为SAR图像解译,电子信箱:liboying.fhyt@sjtu.edu.cn

收稿日期: 2017-09-25

  修回日期: 2017-10-10

  网络出版日期: 2017-10-31

基金资助

国家自然科学基金重点项目(61331015)

Ship geometric parameter extraction for Sentinel-1 dual-polarization products

  • LI Boying ,
  • LIU Bin ,
  • GUO Weiwei ,
  • ZHANG Zenghui ,
  • YU Wenxian
Expand
  • Shanghai Key Laboratory of Intelligent Sensing and Recognition, Shanghai Jiao Tong University, Shanghai 200240, China

Received date: 2017-09-25

  Revised date: 2017-10-10

  Online published: 2017-10-31

摘要

舰船目标几何特性提取是合成孔径雷达(SAR)图像海上目标检测识别的重要基础。在具有几何真值样本的基础上,通过参数寻优和拟合回归,能够提高几何特性提取的精度,这在TerraSAR-X数据上已有研究。本文考虑Sentinel-1大部分情况下均能提供双极化数据这一特点,探索双极化信息能否进一步提升几何特性提取的精度。基于OpenSARShip测试库,首先使用二维度滤波进行图像处理,该图像处理过程中的关键参数使用交叉熵方法进行寻优,在大样本基础上,得到最优参数;之后,在目标几何特性的图像处理提取结果上,综合传感器、环境、目标3方面信息,特别是融合双极化信息,使用多元线性回归模型进行拟合,得到比仅用单极化信息更高的几何特性提取精度,证实了双极化信息的可用性。

本文引用格式

李博颖 , 柳彬 , 郭炜炜 , 张增辉 , 郁文贤 . Sentinel-1双极化数据舰船目标几何特性提取[J]. 科技导报, 2017 , 35(20) : 94 -101 . DOI: 10.3981/j.issn.1000-7857.2017.20.010

Abstract

The ship geometric parameter extraction is an essential basis for the marine target detection and classification for the Synthetic Aperture Radar(SAR) images. With the assistance of the ground true value sample of the marine target size, the improvement of the geometric dimension extraction can be achieved by the parameter optimization and regression, as verified in TerraSAR-X datasets. Taking into consideration of the typical characteristics of the dual-polarization for the sentinel-1 products, this paper explores the usefulness of the dual-polarization fusion information. Based on the OpenSARShip, firstly we utilize a two-dimensional filter method for image processing. The parameters in the image processing are optimized by a cross-entropy method based on the large dataset. Next, with the preliminary extraction results, we combine the information from the sensors, the environment and the target, and especially the information from the dual-polarization. We employ a multiple linear regression model to obtain the precise physical dimensions. The size extraction performance by the dual-polarization fusion information is much better than merely using the single-polarization information, which proves the usefulness of the dual polarization information.

参考文献

[1] Torres R, Snoeij P, Geudtner D, et al. GMES Sentinel-1 mission[J]. Re-mote Sensing of Environment, 2012, 120:9-24.
[2] Malenovsky Z, Rott H, Cihlar J, et al. Sentinels for science:Potential of Sentinel-1,-2, and-3 missions for scientific observations of ocean, cryo-sphere, and land[J]. Remote Sensing of Environment, 2012, 120:91-101.
[3] Imperatore P, Azar R, Calò F, et al. Effect of the vegetation fire on backscattering:An investigation based on Sentinel-1 observations[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Re-mote Sensing, 2017, 10(10):4478-4492.
[4] Mouginot J, Rignot E, Scheuchl B, et al. Comprehensive annual ice sheet velocity mapping using Landsat-8, Sentinel-1, and RADARSAT-2 Data[J]. Remote Sensing, 2017, 9(4):364.
[5] Hornacek M, Wagner W, Sabel D, et al. Potential for high resolution systematic global surface soil moisture retrieval via change detection us-ing Sentinel-1[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(4):1303-1311.
[6] Lohberger S, Stangel M, Atwood E C, et al. Spatial evaluation of Indone-sia's 2015 fire-affected area and estimated carbon emissions using Sentinel-1[J]. Global Change Biology, 2017, doi:10.1111/gcb.13841.
[7] Delgado-Aguilar M J, Fassnacht F E, Peralvo M, et al. Potential of Ter-raSAR-X and Sentinel 1 imagery to map deforested areas and derive degradation status in complex rain forests of Ecuador[J]. International Forestry Review, 2017, 19(1):102-118.
[8] Margarit M G. Marine applications of SAR polarimetry[M]. Barcelona:Universitat Politècnica de Catalunya, 2007.
[9] Messina M, Greco M, Fabbrini L, et al. Modified Otsu's algorithm:A new computationally efficient ship detection algorithm for SAR images[C]//2012 Tyrrhenian Workshop on Advances in Radar and Remote Sensing (TyWRRS). Piscataway, NJ:IEEE, 2012:262-266.
[10] Chen X, Guan J, Bao Z, et al. Detection and extraction of target with micromotion in spiky sea clutter via short-time fractional Fourier transform[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(2):1002-1018.
[11] 陈小龙, 关键, 何友. 微多普勒理论在海面目标检测中的应用及展望[J]. 雷达学报, 2013, 2(1):123-134. Chen Xiaolong, Guan Jian, He You, et al. Applications and prospect of micro-motion theory in the detection of sea surface target[J]. Jour-nal of Radars, 2013, 2(1):123-134.
[12] 陈小龙, 关键, 黄勇, 等. 雷达低可观测目标探测技术[J]. 科技导报, 2017, 35(11):30-38. Chen Xiaolong, Guan Jian, Huang Yong, et al. Radar low-observable target detection[J]. Science & Technology Review, 2017, 35(11):30-38.
[13] Stasolla M, Mallorqui J J, Margarit G, et al. A comparative study of op-erational vessel detectors for maritime surveillance using satelliteborne synthetic aperture radar[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(6):2687-2701.
[14] Tings B, Bentes da Silva C A, Lehner S. Dynamically adapted ship pa-rameter estimation using TerraSAR-X images[J]. International Journal of Remote Sensing, 2016, 37(9):1990-2015.
[15] Stasolla M, Greidanus H. The exploitation of Sentinel-1 images for vessel size estimation[J]. Remote Sensing Letters, 2016, 7(12):1219-1228.
[16] Sciotti M, Pastina D, Lombardo P. Polarimetric detectors of extended targets for ship detection in SAR images[C]//2001 IEEE International Geoscience and Remote Sensing Symposium(IGARSS). Piscataway, NJ:IEEE, 2001, 7:3132-3134.
[17] Novak L M, Burl M C. Studies of target detection algorithms that use Polarimetric radar data[J]. IEEE Transactions on Aerospace and Electronic Systems, 1989, 25(2):150-165.
[18] Novak L M, Burl M C. Optimal speckle reduction in POL-SAR imag-ery and its effect on target detection[C]//1989 Orlando Symposium. Or-lando:International Society for Optics and Photonics. New York:SPIE, 1989:84-115.
[19] Cloude S R, Pottier E. A review of target decomposition theorems in radar polarimetry[J]. IEEE Transactions on Geoscience and Remote Sensing, 1996, 34(2):498-518.
[20] Sugimoto M, Ouchi K, Nakamura Y. On the novel use of model-based decomposition in SAR polarimetry for target detection on the sea[J]. Remote sensing letters, 2013, 4(9):843-852.
[21] Nunziata F, Migliaccio M, Brown C E. Reflection symmetry for polari-metric observation of man-made metallic targets at sea[J]. IEEE Jour-nal of Oceanic Engineering, 2012, 37(3):384-394.
[22] Velotto D, Nunziata F, Migliaccio M, et al. Dual-polarimetric Ter-raSAR-X SAR data for target at sea observation[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(5):1114-1118.
[23] Chen W, Ji K, Xing X, et al. Ship recognition in high resolution SAR imagery based on feature selection[C]//Computer Vision in Remote Sensing (CVRS), 2012 International Conference on. Piscataway, NJ:IEEE, 2012:301-305.
[24] Wang C, Zhang H, Wu F, et al. A novel hierarchical ship classifier for COSMO-SkyMed SAR data[J]. IEEE Geoscience and Remote Sens-ing Letters, 2014, 11(2):484-488.
[25] Kang M, Leng X, Lin Z, et al. A modified faster R-CNN based on CFAR algorithm for SAR ship detection[C]//2017 International Work-shop on Remote Sensing with Intelligent Processing (RSIP). Piscat-away, NJ:IEEE, 2017:1-4.
[26] Xu F, Jin Y Q, Moreira A. A preliminary study on SAR advanced in-formation retrieval and scene reconstruction[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(10):1443-1447.
[27] Velotto D, Bentes C, Tings B, et al. Comparison of Sentinel-1 and Ter-raSAR-X for ship detection[C]//2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Piscataway, NJ:IEEE, 2015:3282-3285.
[28] Vachon P W, Wolfe J. GMES Sentinel-1 analysis of marine applica-tions potential(AMAP)[R/OL].[2017-08-31]. http://cradpdf.drdc-rddc.gc.ca/PDFS/unc79/p530368.pdf.
[29] Olsen R B, Wahl T. The role of wide swath SAR in high-latitude coastal management[J]. Johns Hopkins APL Technical Digest, 2000, 21(1):136-140.
[30] Smith B H. An analytic nonlinear approach to sidelobe reduction[J]. IEEE Transactions on Image Processing, 2001, 10(8):1162-1168.
[31] Liu P, Jin Y Q. A study of ship rotation effects on SAR image[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(6):3132-3144.
[32] Margarit G, Mallorqui J J, Fortuny-Guasch J, et al. Exploitation of ship scattering in polarimetric SAR for an improved classification un-der high clutter conditions[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(4):1224-1235.
[33] Margarit G, Mallorqui J J, Fortuny-Guasch J, et al. Phenomenological vessel scattering study based on simulated inverse SAR imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(4):1212-1223.
[34] Wang E, Kurniawati H, Kroese D P. CEMAB:A Cross-Entropy-based method for large-scale multi-armed bandits[C]//Australasian Confer-ence on Artificial Life and Computational Intelligence. Australasian:Springer International Publishing, 2017:353-365.
[35] Kroese D P, Rubinstein R Y, Cohen I, et al. Cross-entropy method[M]//Encyclopedia of Operations Research and Management Science. New York:Springer, 2013:326-333.
[36] Huang L, Liu B, Li B, et al. OpenSARShip:A dataset dedicated to Sentinel-1 ship interpretation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, in press.
文章导航

/