首页 | 本学科首页   官方微博 | 高级检索  
     

大尺度高分辨率遥感图像机场目标的快速识别
引用本文:李金宗.大尺度高分辨率遥感图像机场目标的快速识别[J].光电子.激光,2010(7):1083-1088.
作者姓名:李金宗
作者单位:哈尔滨工业大学图像信息技术与工程研究所;
基金项目:“十一五”总装重点资助项目(51322020703)
摘    要:基于对机场的图像特征、目标特征的全面分析,提出了一种从大幅面高分辨率光学遥感图像(10000×10000 pixel)中快速识别机场目标的算法。首先通过预处理去除图像中大部分与目标特性不相关的区域,然后在剩余区域中作精确的检测,其中用到的目标特征有空间频率、均值、方差和能量等,使用canny边缘检测、线段分割与四邻域跟踪技术对目标进行精确识别。研究结果表明,本文算法能够实现对机场的快速识别,识别算法时间小于2 s。

关 键 词:大图像  线性特征  快速识别

Fast airport recognition in large scale remote image with high resolution
LI Jin-zong.Fast airport recognition in large scale remote image with high resolution[J].Journal of Optoelectronics·laser,2010(7):1083-1088.
Authors:LI Jin-zong
Affiliation:LI Jin-zong,MU Li-sheng,LI Dong-dong,MA Dong-dong(Institute of Image Information Technology and Engineering,Harbin Institute of Technology,Harbin 150001,China)
Abstract:In addition to the complete analysis of characteristics of image and target,a fast airport target recognition algorithm in large scale remote image with high resolution is presented.First,the irrelevant region to target is erased;secondly the target is recognized accurately in the rest region.Four types of target characteristics are used to preprocess the block image:spatial frequency,average,variance and energy.Accurate target recognition is performed by canny edge detection,straight line extraction and fo...
Keywords:big image  linear character  fast recognition  
本文献已被 CNKI 等数据库收录!
点击此处可从《光电子.激光》浏览原始摘要信息
点击此处可从《光电子.激光》下载全文
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