首页 | 本学科首页   官方微博 | 高级检索  
     

一种基于模糊决策的矩形目标提取算法
引用本文:毛峡,赵兴圆,沈巍. 一种基于模糊决策的矩形目标提取算法[J]. 北京航空航天大学学报, 2008, 34(6): 699-702
作者姓名:毛峡  赵兴圆  沈巍
作者单位:北京航空航天大学 电子信息工程学院, 北京 100191
摘    要:
航空图片中的城市建筑物屋顶一般为矩形或平行四边形,能准确而快速地提取矩形,无论在军事上还是民用上都具有非常重要的意义.针对从航空图像中自动提取矩形建筑物目标的问题,提出了一种基于模糊决策的矩形目标提取方法.首先根据直线提取方法得到的直线特征集生成假设矩形空间,进而采用模糊数学方法进行证据融合得到决策信息,并对生成的假设矩形进行选择与验证,得到矩形目标结构特征.实验结果表明,该算法避免了固定阈值的设定,适应性强,鲁棒性好,有较强的实际应用价值. 

关 键 词:矩形建筑物   感知分组   模糊决策   阈值
收稿时间:2007-05-22

Extraction method of rectangular building based on fussy decision-making
Mao Xia Zhao,Xingyuan,Shen Wei. Extraction method of rectangular building based on fussy decision-making[J]. Journal of Beijing University of Aeronautics and Astronautics, 2008, 34(6): 699-702
Authors:Mao Xia Zhao  Xingyuan  Shen Wei
Affiliation:School of Electronics and Information Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
Abstract:
The roof of the building in aerial image is generally rectangle or parallelogram.It makes a significance sense to extract the rectangle accurately and fast,either in military aspect or in civilian aspect.A method based on fussy decision-making for extraction of rectangular buildings from the aerial images was proposed.Firstly,the presumed rectangular space was generated via line feature,which was resulted from beeline-extraction of the aerial image.Then,the support evidences which were get from the image were combined by fussy mathematic method in order to obtain decision-making information.Finally,the generated rectangle was selected and validated according to the decision-making information.This arithmetic uses the non-fixed threshold value to select the supporting evidences to improve the validity.The results of performance assessment also possess the robustness and high extraction rate of the approach developed.
Keywords:rectangle building  perceptual grouping  fussy decision-making  threshold
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《北京航空航天大学学报》浏览原始摘要信息
点击此处可从《北京航空航天大学学报》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