Please wait a minute...
img

官方微信

遥感技术与应用  2004, Vol. 19 Issue (6): 461-466    DOI: 10.11873/j.issn.1004-0323.2004.6.461
技术方法     
SAR图像中海上舰船目标自动检测新方法
胡应添,徐守时,黄戈祥,吴秀清
(中国科学技术大学电子工程和信息科学系, 安徽 合肥 230027)
A New Method for Automatic Detection of ShipTargets in SAR Images
HU Ying-tian, XU Shou-shi, HUANG Ge-xiang, WU Xiu-qing
 (Department of Electronic Engineering and Information Science,USTC,Hefei230027,China)
 全文: PDF 
摘要:

针对中分辨率近岸海域SAR图像,结合已有的舰船检测算法,提出了一种新的海上舰船目标自动检测方法。该方法先根据相应的抽取算法和图像数据映射准则,分离图像中的海洋和陆地区域,并结合最大熵分割法提取海洋背景中包含候选目标的感兴趣区域,最后利用特征匹配方法检测出真正的舰船目标。对50多幅SAR图像进行了试验,其结果表明该方法能自动、快速、准确地检测出图像中舰船目标。

关键词: SAR自动目标检测视觉特性特征匹配    
Abstract:

Automatic interpretation of synthetic aperture radar (SAR) images is one of the most interesting andimportant application fields in image processing. Focusing on the medium resolution SAR images and combiningwith the previous algorithms, a novel technique to detecting ship targets from coastal regions in a fully automat-ic way is proposed in this paper. This paper presents current progress made on the detection model. In thismethod, sea regions and land regions were detected firstly according to the corresponding decimation algorithmand thresholding technique. Then the land regions can be masked out from the SAR image based on mappingprinciple of the image datas. And In order to obtain a high reliability and robustness, the processed processingchain detects possible targets by first searching in parallel for bright spots, i.e. potential ship bodies. There-fore, the sea image with ship targets is processed with maximum entropic algorithm, and we can extract the re-gions of interest which contain candidate ship targets. And the authentic ship targets were eventually detectedby utilizing the method of feature matching. Finally, for later classification and recognition we calculate the fea-ture parameters of every ship. Experimental results on 50 different SAR images are given to demonstrate thatthis method can automatically detect ship targets from SAR images with high efficiency.

Key words: SAR    Automatic target detection    Visual characteristic    Feature matching
收稿日期: 2004-03-12 出版日期: 2011-12-26
:  TN 958   
基金资助:

中科院知识创新工程项目(项目编号:KZCX0101)资助。

作者简介: 胡应添(1980-),男,硕士生,研究方向为图像分析与理解,计算机视觉、多传感器数据融合等。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

胡应添,徐守时,黄戈祥,吴秀清. SAR图像中海上舰船目标自动检测新方法[J]. 遥感技术与应用, 2004, 19(6): 461-466.

HU Ying-tian, XU Shou-shi, HUANG Ge-xiang, WU Xiu-qing. A New Method for Automatic Detection of ShipTargets in SAR Images. Remote Sensing Technology and Application, 2004, 19(6): 461-466.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2004.6.461        http://www.rsta.ac.cn/CN/Y2004/V19/I6/461

〔1〕 Rey M T, Drosopoulous T, Petrovic D. A Search Procedure forShip RADARSAT Imagery〔J〕. DREO Report 1996, 1305: 48~52.〔2〕 Kouti, Shepherd, SchWartz. Intergrating Spaceborne SAR Im-agery into Operational System for Fisheries Monitoring〔J〕.Canadian Journal of Remote Sensing, 2001,27(5):291~305.〔3〕 Wackerman C, Friedman K, Pichel W.Automatic Ship Detection in RADARSAT SAR Imagery〔J〕. Canadian Journal of Remote Sensing,2001,27(5):371~378.〔4〕 Eldhuset Knut. An Automatic Ship and Ship Wake DetectionSystem for Spaceborne SAR Image in Costal Regions〔J〕. IEEETrans on Geoscience and Remote Sensing,1996,34(4):1010~1019.〔5〕 Qingshan, JiangShengrui. Ship Detection in Radarsat SAR Imagery〔J〕.IEEE Transactions on Geoscience and Remote Sense, 1990, 28(4): 4562~4566.〔6〕 Rey M, Tunaley J K, Folinsbee J T,et al. Application of RadonTransform Techniques to Wake Detection of Seasat-A SAR Images〔J〕. IEEE Transactions on Geoscience and Remote Sense,1990,28(4):553~560.〔7〕 Weszka, Ronsenfeld, Histogram modification for threshold selection〔J〕.IEEE, 1979,8:38~72.〔8〕 Kapur J N, Sahoo P K, Wong A K C. A New Method of Gray-level Picture Thresholding Using the Entropy of the Histogram〔J〕. Computer Vision, Graphics, and Image Processing, 1985,29(2):273~285〔9〕 Hu M K. Visual Pattern Recognition by Moment Invariants〔J〕.IEEE Trans Info Theory, 1962,8:179~187.

[1] 李姣姣,刘玉,陈锟山. 基于香农熵的极化SAR相干矩阵信息量评价#br#[J]. 遥感技术与应用, 2018, 33(5): 842-849.
[2] 王常颖,田德政,韩园峰,隋毅,初佳兰. 基于属性差决策树的全极化SAR影像海冰分类[J]. 遥感技术与应用, 2018, 33(5): 975-982.
[3] 郭欣,赵银娣. 基于Sentinel-1A SAR的湖南省宁乡市洪水监测[J]. 遥感技术与应用, 2018, 33(4): 646-656.
[4] 张程,张红,王超. 基于PCDM香农熵的全极化SAR图像船舶目标检测方法[J]. 遥感技术与应用, 2018, 33(3): 499-507.
[5] 刘建歌,慕德俊. 基于SAR影像海冰动态特征的提取方法[J]. 遥感技术与应用, 2018, 33(1): 55-60.
[6] 张王菲,陈尔学,李增元,赵磊,姬永杰. 干涉、极化干涉SAR技术森林高度估测算法研究进展[J]. 遥感技术与应用, 2017, 32(6): 983-997.
[7] 周晓宇,陈富龙. 四川大熊猫栖息地PALSAR时序数据森林覆盖动态监测研究[J]. 遥感技术与应用, 2017, 32(6): 1100-1106.
[8] 扎西央宗,李林,卓玛,冯岩,李学东,白玛央宗. 西藏年楚河流域冰川变化监测方法研究[J]. 遥感技术与应用, 2017, 32(6): 1126-1131.
[9] 姜爱辉,刘国林,陈富龙. 基于PALSAR-1影像的汉函谷关遗迹变化检测研究[J]. 遥感技术与应用, 2017, 32(5): 787-793.
[10] 尤江彬,陈富龙. 西域都护府/且末古城数字地望考与长波段雷达次地表考古初探[J]. 遥感技术与应用, 2017, 32(5): 794-800.
[11] 张宝华,周文涛,吕晓琪. 基于稀疏分解和改进MRF模型的SAR海冰图像分割方法[J]. 遥感技术与应用, 2017, 32(4): 709-713.
[12] 王苏芸,孙中昶,郭华东,申维. 基于面向对象的东营市城乡建设用地信息提取[J]. 遥感技术与应用, 2017, 32(4): 780-786.
[13] 孙亚勇,黄诗峰,李纪人,李小涛,马建威,曲伟. Sentinel-1A SAR数据在缅甸伊洛瓦底江下游区洪水监测中的应用[J]. 遥感技术与应用, 2017, 32(2): 282-288.
[14] 王娜,李强子,赵龙才,王红岩,李德江,黄慧萍. 基于变异系数法的SAR船舶检测优化研究[J]. 遥感技术与应用, 2017, 32(2): 305-314.
[15] 肖瑶,赵萍,范泽琳,陈国旭. TerraSAR-X数据在淮南矿区沉陷监测中的应用[J]. 遥感技术与应用, 2017, 32(1): 95-103.