航空遥感影像的实时舰船目标检测

姜鑫; 陈武雄; 聂海涛; 郝志成

doi:10.37188/OPE.20202810.2360

您当前的位置：

首页 >

文章列表页 >

航空遥感影像的实时舰船目标检测

信息科学 | 更新时间：2020-11-16

- 航空遥感影像的实时舰船目标检测
- Real-time ship target detection based on aerial remote sensing images
- 光学精密工程 2020年28卷第10期页码：2360-2369
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
  2.重庆嘉陵华光光电科技有限公司, 重庆 400700
- 作者简介：
  
  [ "姜鑫(1992-), 男, 吉林长春人, 硕士, 研究实习员, 2015年和2018年于浙江大学分别获得学士学位和硕士学位, 主要从事图像处理及人工智能方面的研究。E-mail:xinjiang@zju.edu.cn" ]
- 基金信息：
  
  广东省重点领域研发计划资助项目(2019B010155003)
- DOI：10.37188/OPE.20202810.2360
  中图分类号： TP751.1
- 收稿日期：2020-05-29，
  
  修回日期：2020-06-23，
  
  录用日期：2020-6-23，
  
  纸质出版日期：2020-10-25
- 稿件说明：
移动端阅览
姜鑫, 陈武雄, 聂海涛, 等. 航空遥感影像的实时舰船目标检测[J]. 光学精密工程, 2020,28(10):2360-2369.

Xin JIANG, Wu-xiong CHEN, Hai-tao NIE, et al. Real-time ship target detection based on aerial remote sensing images[J]. Optics and precision engineering, 2020, 28(10): 2360-2369.
姜鑫, 陈武雄, 聂海涛, 等. 航空遥感影像的实时舰船目标检测[J]. 光学精密工程, 2020,28(10):2360-2369. DOI： 10.37188/OPE.20202810.2360.

Xin JIANG, Wu-xiong CHEN, Hai-tao NIE, et al. Real-time ship target detection based on aerial remote sensing images[J]. Optics and precision engineering, 2020, 28(10): 2360-2369. DOI： 10.37188/OPE.20202810.2360.

摘要

舰船是重要的海上目标，航空遥感影像的实时舰船目标检测在民用领域和国防安全中均具有十分重要的意义和价值。以工程应用为背景，重点对航空遥感影像的海陆分割和舰船检测两方面问题展开研究。利用灰度信息对遥感影像进行自适应阈值分割，结合形态学算子和孔洞填充技术，实现海陆分割；利用舰船几何结构特征进行直线段检测，结合K均值密度聚类技术，完成舰船目标检测。实验结果表明：针对海陆分割任务，陆地检测率为95.8%，陆地检测错误率为5.7%，陆地检测正确率为94.4%；针对舰船目标检测任务，检测准确率为94.1%，检测虚警率为3.9%。可以较好地将影像中的海洋区域和陆地区域分割成两个相互独立的部分，分割效果理想；同时可以快速地完成舰船目标检测，准确率高，虚警率低，具有运算简单、易于工程实现等特点。

Abstract

Ships are vital marine targets. Real-time ship target detection based on aerial remote-sensing images is useful in civil engineering as well as national defense security. Based on the engineering application background

land-sea segmentation and ship detection was investigated in this study using aerial remote-sensing images. Gray-scale information was used to segment the remote-sensing images with adaptive threshold; the morphological operator and hole-filling technique were combined to achieve land-sea segmentation. Furthermore

ship geometry features were used to detect the straight-line segment

and K-means density clustering was applied to complete the ship target detection. The experimental results showed that for land-sea segmentation

the land detection rate was 95.8%

the land detection error rate was 5.7%

and the land detection accuracy rate was 94.4%. For ship target detection

the detection accuracy rate was 94.1%

and the detection false alarm rate was 3.9%. The proposed technique effectively segmented the ocean and land areas of the images

and the segmentation effect was ideal. The proposed technique had the following advantages: rapid ship target detection

high accuracy

low false alarm rate

simple calculation

and easy engineering applicability.

关键词

Keywords

references

曹佃生 , 石振华 , 林冠宇 . 机载海洋改进型Dyson高光谱成像仪的研制 . 光学精密工程 , 2017 . 25 ( 6 ): 1403 - 1409 . http://ope.lightpublishing.cn/thesisDetails?columnId=1407648&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1407648&Fpath=&index=-1&l=zh .

D SH CAO , ZH H SHI , G Y LIN . Development of airborne ocean modified Dyson hyper spectral imager . Opt. Precision Eng. , 2017 . 25 ( 6 ): 1403 - 1409 . http://ope.lightpublishing.cn/thesisDetails?columnId=1407648&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1407648&Fpath=&index=-1&l=zh .

赵云峰 , 李夜金 , 张寅 , 等 . 海洋背景下运动目标的天基红外探测场景生成系统 . 光学精密工程 , 2017 . 25 ( 4 ): 487 - 493 . http://ope.lightpublishing.cn/thesisDetails?columnId=1406311&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1406311&Fpath=&index=-1&l=zh .

Y F ZHAO , J Y LI , Y ZHANG , 等 . A space-based infrared detection scene generation system for moving objects with sea background . Opt. Precision Eng. , 2017 . 25 ( 4 ): 487 - 493 . http://ope.lightpublishing.cn/thesisDetails?columnId=1406311&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1406311&Fpath=&index=-1&l=zh .

高贤君 , 万幼川 , 郑顺义 , 等 . 航空摄影过程中云的实时自动检测 . 光谱学与光谱分析 , 2014 . 34 ( 7 ): 1909 - 1913 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gpxygpfx201407042 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gpxygpfx201407042 .

X J GAO , Y CH WAN , SH Y ZHENG , 等 . Real time automatic detection of cloud in aerial photography . Spectroscopy and Spectral Analysis , 2014 . 34 ( 7 ): 1909 - 1913 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gpxygpfx201407042 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gpxygpfx201407042 .

尹雅 , 黄海 , 张志祥 . 基于光学遥感图像的舰船目标检测技术研究 . 计算机科学 , 2019 . 46 ( 3 ): 82 - 87 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjkx201903010 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjkx201903010 .

Y YIN , H HUANG , ZH X ZHANG . Research on ship detection technology based on optical remote sensing image . Computer Science , 2019 . 46 ( 3 ): 82 - 87 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjkx201903010 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjkx201903010 .

施鹏.基于光学遥感图像的舰船目标自动检测技术[D].合肥: 中国科学技术大学, 2010.

SHI P. The Ship Detection Based on Optical Remote Sensing Images [D].Hefei: University of Science and Technology of China, 2010.(in Chinese)

徐芳 , 刘晶红 , 曾冬冬 , 等 . 基于视觉显著性的无监督海面舰船检测与识别 . 光学精密工程 , 2017 . 25 ( 5 ): 1300 - 1311 . http://ope.lightpublishing.cn/thesisDetails?columnId=1412878&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1412878&Fpath=&index=-1&l=zh .

F XU , J H LIU , D D ZENG , 等 . Detection and identification of unsupervised ships and warships on sea surface based on visual saliency . Opt. Precision Eng. , 2017 . 25 ( 5 ): 1300 - 1311 . http://ope.lightpublishing.cn/thesisDetails?columnId=1412878&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1412878&Fpath=&index=-1&l=zh .

刘峰 , 沈同圣 , 马新星 , 等 . 基于多波段深度神经网络的舰船目标识别 . 光学精密工程 , 2017 . 25 ( 11 ): 2939 - 2946 . http://ope.lightpublishing.cn/thesisDetails?columnId=1447788&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1447788&Fpath=&index=-1&l=zh .

F LIU , T S SHEN , X X MA , 等 . Ship recognition based on multi-band deep neural network . Opt. Precision Eng. , 2017 . 25 ( 11 ): 2939 - 2946 . http://ope.lightpublishing.cn/thesisDetails?columnId=1447788&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1447788&Fpath=&index=-1&l=zh .

张卡 , 盛业华 , 付素霞 , 等 . 基于物方定位一致性约束的光学航空影像多视铅垂线轨迹匹配 . 光学精密工程 , 2018 . 26 ( 7 ): 1784 - 1793 . http://ope.lightpublishing.cn/thesisDetails?columnId=1420994&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1420994&Fpath=&index=-1&l=zh .

K ZHANG , Y H SHENG , S X FU , 等 . Multi-view VLL matching algorithm for optical aerial images based on constraint of object space positioning consistency . Opt. Precision Eng. , 2018 . 26 ( 7 ): 1784 - 1793 . http://ope.lightpublishing.cn/thesisDetails?columnId=1420994&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1420994&Fpath=&index=-1&l=zh .

储昭亮 , 王庆华 , 陈海林 , 等 . 基于极小误差阈值分割的舰船自动检测方法 . 计算机工程 , 2007 . 33 ( 11 ): 239 - 241 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjgc200711086 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjgc200711086 .

SH L CHU , Q H WANG , H L CHEN , 等 . Ship auto detection method based on minimum error threshold segmentation . Computer Engineering , 2007 . 33 ( 11 ): 239 - 241 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjgc200711086 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjgc200711086 .

SHUAI T, SUN K, WU X, et al .. A ship target automatic detection method for high-resolution remote sensing[C]. IEEE International Geoscience and Remote Sensing Symposium, Beijing, P.R. China: IGARSS , 2016: 1258-1261.

李晓琪.大幅面海洋卫星遥感图像目标检测研究[D].深圳: 深圳大学, 2017.

LI X Q. Research on Target Detection of Large Format Ocean Satellite Remote Sensing Images [D]. Shenzhen: Shenzhen University, 2017.(in Chinese)

于鹏.高分辨率可见光遥感图像舰船目标识别方法研究[D].长春: 吉林大学, 2011.

YU P. Research on the Ship Target Recognition in High Resolution Optical Remote Sensing Image [D]. Changchun: Jilin University, 2011.(in Chinese)

王海涌 , 武文卿 , 薛晓峰 , 等 . 分块峰值点局部区域生长的星象提取 . 光学精密工程 , 2012 . 20 ( 11 ): 2507 - 2515 . http://ope.lightpublishing.cn/thesisDetails?columnId=1762327&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1762327&Fpath=&index=-1&l=zh .

H Y WANG , W Q WU , X F XUE , 等 . Star image extracting based on local region growing around peaks in blocks . Opt. Precision Eng. , 2012 . 20 ( 11 ): 2507 - 2515 . http://ope.lightpublishing.cn/thesisDetails?columnId=1762327&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1762327&Fpath=&index=-1&l=zh .

姜鑫 , 陈武雄 , 朱明 , 等 . 基于实时递推最小二乘的多目标编批研究 . 国外电子测量技术 , 2020 . 39 ( 2 ): 59 - 64 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gwdzcljs202002013 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gwdzcljs202002013 .

X JIANG , W X CHEN , M ZHU , 等 . Research on multi-target serial-number based on least square principle in real-time recursively . Electronic Measurement Technology , 2020 . 39 ( 2 ): 59 - 64 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gwdzcljs202002013 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gwdzcljs202002013 .

彭敬涛.光学遥感图像舰船目标检测技术的研究[D].上海: 东华大学, 2017.

PENG J T. The Study of Ship Target Detection in Optical Remote Sensing Images [D]. Shanghai: Donghua University, 2017.(in Chinese)

裴洪飞.航空图像中舰船目标识别技术研究[D].哈尔滨: 哈尔滨工程大学, 2011.

PEI H F. Researches for Ship Identification in Aerial Images [D]. Harbin: Harbin Engineering University, 2011.(in Chinese)

R GROMPONE , J JAKUBOWICZ , J MOREL , 等 . LSD:A fast line segment detector with a false detection control . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2010 . 32 ( 4 ): 722 - 732 . DOI: 10.1109/TPAMI.2008.300 http://doi.org/10.1109/TPAMI.2008.300 .

L WANG , C PAN . Robust level set image segmentation via a local correntropy-based K-means clustering . Pattern Recognition , 2014 . 47 ( 5 ): 1917 - 1925 . DOI: 10.1016/j.patcog.2013.11.014 http://doi.org/10.1016/j.patcog.2013.11.014 .

张雷 , 冯冲 . 改进指数加权平均比率与小波变换结合的遥感图像海陆分离 . 科学技术与工程 , 2017 . ( 36 ): 211 - 216 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=kxjsygc201736034 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=kxjsygc201736034 .

L ZHANG , CH FENG . Improved ratio of exponentially weighted averages operator combined with wavelet transform for sea-land segmentation in remote sensing image . Science Technology and Engineering , 2017 . ( 36 ): 211 - 216 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=kxjsygc201736034 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=kxjsygc201736034 .

葛娴君 , 张旭 . 一种分策略粗精结合的大视场遥感图像海陆分割方法 . 中国新通信 , 2019 . ( 13 ): 90 - 93 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgsjtx201913069 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgsjtx201913069 .

X J GE , X ZHANG . A segmentation method of land and sea in large field of view remote sensing image based on combination of rough and fine segmentation strategies . China New Telecommunications , 2019 . ( 13 ): 90 - 93 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgsjtx201913069 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgsjtx201913069 .

王慧利 , 朱明 , 蔺春波 , 等 . 光学遥感图像中复杂海背景下的舰船检测 . 光学精密工程 , 2018 . 26 ( 3 ): 723 - 732 . http://ope.lightpublishing.cn/thesisDetails?columnId=1414795&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1414795&Fpath=&index=-1&l=zh .

H L WANG , M ZHU , CH B LIN , 等 . Ship detection of complex sea background in optical remote sensing images . Opt. Precision Eng. , 2018 . 26 ( 3 ): 723 - 732 . http://ope.lightpublishing.cn/thesisDetails?columnId=1414795&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1414795&Fpath=&index=-1&l=zh .

公明 , 刘妍妍 , 李国宁 . 改进YOLO-v3的遥感图像舰船检测方法 . 电光与控制 , 2020 . ( 5 ): 102 - 107 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgykz202005021 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgykz202005021 .

M GONG , Y Y LIU , G N LI . Remote sensing image ship detection method of improved YOLO-v3 . Electronics Optics & Control , 2020 . ( 5 ): 102 - 107 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgykz202005021 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dgykz202005021 .

浏览量

393

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向航天光学遥感复杂场景图像的舰船检测

光学遥感图像中复杂海背景下的舰船检测

基于多尺度多特征视觉显著性的海面舰船检测

航空遥感惯性稳定平台的改进型小脑模型神经网络/比例微分复合控制