首页 | 本学科首页   官方微博 | 高级检索  
     

可见光遥感图像中舰船目标检测方法
引用本文:赵英海,吴秀清,闻凌云,徐守时.可见光遥感图像中舰船目标检测方法[J].光电工程,2008,35(8):102-106.
作者姓名:赵英海  吴秀清  闻凌云  徐守时
作者单位:中国科学技术大学,电子工程与信息科学系,合肥,230027
基金项目:国家高技术研究发展计划(863计划)
摘    要:本文提出了一种基于标准差特征平面Contrast box滤波的可见光遥感图像舰船目标检测方法.选用局部统计方差作为目标检测特征,实现对不同亮度舰船的统一特征描述,并消除海面平均亮度变化的影响.然后在二维检测特征平面上通过Contrast box滤波自适应确定局部目标检测阈值,并结合目标的空间结构信息完成疑似目标定位.最后借助先验舰船特征模型对疑似目标集合进行验证以去除虚警,输出最终目标检测结果.实验结果表明,该方法对于可见光遥感图像中的舰船目标能够达到99.5%的目标检测准确率,同时目标检测虚警率为5%.

关 键 词:可见光图像  舰船目标检测  检测特征  box滤波  目标验证
收稿时间:2007/12/24

Ship Target Detection Scheme for Optical Remote Sensing Images
ZHAO Ying-hai,WU Xiu-qing,WEN Ling-yun,XU Shou-shi.Ship Target Detection Scheme for Optical Remote Sensing Images[J].Opto-Electronic Engineering,2008,35(8):102-106.
Authors:ZHAO Ying-hai  WU Xiu-qing  WEN Ling-yun  XU Shou-shi
Affiliation:ZHAO Ying-hai,WU Xiu-qing,WEN Ling-yun,XU Shou-shi ( Department of Electronics Engineering , Information Science,University of Science , Technology of China,Hefei 230027,China )
Abstract:A ship target detection scheme based on optical remote sensing images of contrast box filtering over the standard deviation feature planes is presented. Firstly, local intensity variance is selected as the detection feature to characterize ships of different intensities uniformly and eliminate the influence of varying sea average intensity at the same time. Secondly, on the two-dimensional detection feature plane, local detection thresholds are estimated self-adaptively by contrast box filtering and the spa...
Keywords:Contrast
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号