大尺度高分辨率遥感图像机场目标的快速识别  

Fast airport recognition in large scale remote image with high resolution

作　　者：李金宗[1] 穆立胜[1] 李冬冬[1] 马冬冬[1] 

机构地区：[1]哈尔滨工业大学图像信息技术与工程研究所,黑龙江哈尔滨150001

出　　处：《光电子．激光》2010年第7期1083-1088,共6页Journal of Optoelectronics·Laser

基　　金："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。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 four neighbours tracing.The method presented in this paper realizes fast airport recognition in large scale remote image with high resolution,and the recognition time is less than 2 s.

关 键 词：大图像 线性特征 快速识别 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]