Computer Science

Computer Science ›› 2021, Vol. 48 ›› Issue (6A): 132-136.doi: 10.11896/jsjkx.200700180

• Image Processing & Multimedia Technology • Previous Articles     Next Articles

Optimization Algorithm of Ship Detection Based on Multi-feature in SAR Images

YAN Jun1, FENG Su-yun1, LU Lin-lin2, WANG Qing3, CAI Ming-xiang1   

  1. 1 Zhuhai Orbita Aerospace Science Technology Co.,Ltd.,Zhuhai,Guangdong 519080,China
    2 Key Laboratory of Digital Earth Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China
    3 93114 Unit of the Chinese People's Liberation Army,Beijing 100195,China
  • Online:2021-06-10 Published:2021-06-17
  • Contact: YAN Jun,born in 1962,Ph.D.His main research interests include remote sen-sing technology and application and so on.
    LU Lin-lin,born in 1984,Ph.D,asso-ciate professor.Her main research interests include urban remote sensing,remote sensing information extraction and classification.
  • Supported by:
    Local Innovative and Research Teams Project of Guangdong Pearl River Talent Program(2017BT01G115),Zhuhai City Social Development Field Science and Technology Plan Project(ZH22036203200023PWC),Strategic Priority Research Program of Chinese Academy of Sciences (XDA19090107),National Natural Science Foundation of China (41471369) and National Key Research and Development Program(2017YFE0100800).

PDF (PC)

749

Abstract: In view of that the traditional ship detection algorithms cannot effectively avoid the influence of the side lobe effect on results,which mostly consider the gray contrast between the ship and the background.The geometric characteristics of the target object on the SAR images are not fully utilized,and the detection accuracies are low,therefore a target detection algorithm based on the ship's multi-features is proposed.The azimuth estimation method and the stepwise approximation method are used to eliminate the influence of the side lobe effect on the geometric characteristics (area,aspect ratio and rectangularity) and gray contrast,and then the variance coefficient method is used to distribute different weight for the four features to calculate the confidence.By determining the best confidence threshold to remove the non-target objects among the candidate targets and optimize the detection results,this paper uses Sentinel-1 images to verify the algorithm,the two-parameter CFAR algorithm and the KSW double-threshold algorithm are used as comparative experiments.The experimental results show that for three images with different background complexities,the quality factor of the proposed algorithm exceeds 0.7 with the minimum calculation time,and it maintains optimal detection performance for images with complex background.

Key words: Azimuth estimation, Minimum bounding rectangle, Sentinel-1, Ship detection, Weight allocation

CLC Number: 

  • TP753
[1] YIN Y,HUANG H,ZHANG Z X.Research on ship detection technology based on optical remote sensing image[J].Computer Science,2019,46(3):82-87.
[2] DING R L,LI J,ZHANG M,et al.Shiptarget detection in remote sensing image based on S-HOG[J/OL].[2020-10-29].http://kns.cnki.net/kcms/detail/50.1075.TP.20200630.1726.002.html.
[3] ZHOU N,TIAN J W.Research on multi feature fusion infrared ship wake detection[J].Computer Science,2018,45(S2):172-175.
[4] ZHAI L,LI Y,SU Y.A method for ship detection in SAR images based on anomaly detection and two-layer censoring mechanism[J].Computer Engineering,2017,43(4):244-250.
[5] ZHOU Y Y,CHENG J H,LIU T,et al.Review of road extraction for high-resolution SAR images[J].Computer Science,2020,47(1):124-135.
[6] ZHANG X Q.Study on ship detection within harbor areasinSAR images [D].Harbin:National University of Defense Technology,2014.
[7] SHI Z P,WU J,PENG F,et al.Performance analysis about automatic of SAR image based on CFAR method in frequency-domain[J].Computer Engineering and Applications,2012,48(15):107-112,137.
[8] WANG H,CHEN X,TIAN S Z,et al.SAR image recognition based on few-shot learning[J].Computer Science,2020,47(5):124-128.
[9] YU Y,WANG B,ZHANG L.Hebbian-based neural networksfor bottom-up visual attention and its applications to ship detection in SAR images[J].Neurocomputing,2011,74(11):2008-2017.
[10] CHEN LF,LIU Y Z,ZHANG P,et al.Road extraction algorithm of multi-feature migh-resolution SAR image based on Multi-Path RefineNet[J].Computer Science,2020,47(3):156-161.
[11] ZHANG Z F,ZHAO Z,WEI J J,et al.A method for ship detection in SAR imagery based on improved human visual attention system[J].Science of Surveying and Mapping,2017,42(4):108-112.
[12] ZHANG M C,WU X Q,WANG P W.An adaptive approach for target detection in SAR images[J].Computer Engineering and Applications,2006(10):200-203.
[13] ZHAO Q H,WANG X,LI Y,et al.Ship detection optimization method in SAR imagery based on multi-feature weighting[J].Journal on Communication,2020,41(3):91-101.
[14] DU L,WANG Z C,WANG Y,et al.Survey of research progresson target detection and discrimination of single-channel SAR images for complex scenes[J].Journal of Radars,2020,9(1):34-54.
[15] CHEN S,WANG H,XU F,et al.Target classification using the deep convolutional networks for SAR images[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(8):4806-4817.
[16] BENTES C,VELOTTO D,TINGS B.Ship classification in TerraSAR-X images with convolutional neural networks[J].IEEE Journal of Oceanic Engineering,2017,PP(99):1-9.
[17] NIU L.Sidelobe removal method for ship target based on SAR images[J].Radar Science and Technology,2018,16(2):197-200.
[18] GAO D,HAN S,VASCONCELOS N.Discriminant saliency,the detection of suspicious coincidences,and applications to visual recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2009,31(6):989-1005.
[19] WANG X H.Moment technique and its applications in imageprocessing and recognition[D].Xi'an:Northwestern Polytechnical University,2002.
[20] XIONG W,XU Y L,CUI Y Q,et al.Geometric feature extractionof ship in high-resolution synthetic aperture Radar images[J].Acta Photonica Sinica,2018,47(1):55-64.
[21] ZHEN Y,LIU W,CHEN J H,et al.Geometric structure feature extraction ofship target in high-resolution SAR image[J].Journal of Signal Processing,2016,32(4):424-429.
[22] PAPATSOUMA I,FARMAKIS N.Approximating SymmetricDistributions via Sampling and Coefficient of Variation[J].Communications in Statistics,2020,49(1):61-77.
[23] AI J,YANG X,SONG J,et al.An adaptively truncated clutter-statistics-based two-parameter CFAR detector in SAR imagery[J].IEEE Journal of Oceanic Engineering,2017,PP(99):1-13.
[24] XIONG W,XU Y l,YAO L B,et al.A new ship target detection algorithm based on SVM in high resolution SAR images[J].Remote Sensing Technology and Application,2018,33(1):119-127.
[25] ZHAO Z,JI K,XING X,et al.Adaptive CFAR detection of ship targets in high resolution SAR imagery[J].Proceedings of Spie the International Society for Optical Engineering,2013,8917:89170L-89170L-8.
[1] XU Hua-chi, SHI Dian-xi, CUI Yu-ning, JING Luo-xi, LIU Cong. Time Information Integration Network for Event Cameras [J]. Computer Science, 2022, 49(5): 43-49.
[2] HUANG Yong-tao, YAN Hua. Scene Graph Generation Model Combining Attention Mechanism and Feature Fusion [J]. Computer Science, 2020, 47(6): 133-137.
[3] DING Rong-li, LI Jie, ZHANG Man, LIU Yan-li, WU Wei. Ship Target Detection in Remote Sensing Image Based on S-HOG [J]. Computer Science, 2020, 47(11A): 248-252.
[4] LING Chen, ZHANG Xin-tong, MA Lei. Remote Sensing Image Processing Technology and Its Application Based on Mask R-CNN Algorithms [J]. Computer Science, 2020, 47(10): 151-160.
[5] YIN Ya, HUANG Hai, ZHANG Zhi-xiang. Research on Ship Detection Technology Based on Optical Remote Sensing Image [J]. Computer Science, 2019, 46(3): 82-87.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.