Please wait a minute...
img

官方微信

遥感技术与应用  2012, Vol. 27 Issue (2): 190-196    DOI: 10.11873/j.issn.1004-0323.2012.2.190
图像与数据处理     
基于特征线匹配的城市建筑物识别方法研究
李松霖1,范海生2,陈秀万1
(1.北京大学遥感与地理信息系统研究所,北京 100871;2.中国科学院遥感应用研究所遥感云服务研究中心,广东 东莞 520808)
Research of Urban Building Recognition Method based on Line Features Matching
Li Songlin1,Fan Haisheng2,Chen Xiuwan1
(1.Institution of Remote Sensing and GIS,Peking University,Beijing 100871,China;2.Research Center of Remote Sensing Cloud Services,Institute of Remote Sensing Application,Chinese Academy of Sciences,Dongguan 520808,China)
 全文: PDF(2086 KB)  
摘要:

随着手机GPS位置测定、导航以及摄像功能的普及,对于移动状态下的位置定位以及都市空间建筑物实时搜索等应用功能存在日益增长的需求。介绍了图像处理方式的城市建筑物识别方法,通过对两种图像匹配算法——SIFT和Local Search的比较分析表明,构造物轮廓线及其组合是一种相对稳定的几何特征,在匹配时受图像的仿射变换、画质变化以及镜头畸变等因素干扰较小,此外,基于轮廓的图像匹配指数还能反映摄影位置的变化。因此,对Local Search进行了改进,利用实时图的建筑物的特征轮廓线与从三维数据库中提取的建筑群特征轮廓线进行匹配,然后选择匹配指数高的记录作为识别结果。结果表明基于Local Search算法的建筑物识别技术可以很好地适应移动条件下建筑物快速识别的要求。

关键词: 城市建筑物识别SIFT算法Local Search算法特征线匹配建筑物天际轮廓线    
Abstract:

With the popularity of cell phones having functions of GPS positioning,navigation and camera,there exist increasing demands for real-time identification of urban buildings with mobile terminals.In this paper,image processing algorithms for urban buildings recognition,including SIFT and Local Search,were discussed and compared in details to show that contour lines and their combinations are stable geometric features of buildings,so the algorithms based on contour lines immune to affine transformation,low picture qualities and lens distortion.Besides,the match index based on contour lines can reflect the camera position change.As a result,Local Search was improved;firstly getting the building contour lines by abstracted from pictures photographed by mobile terminals and generated from the 3D-database,secondly utilizing it to find some of the best matches between  those contour lines.The improved algorithm can meet the demand of fast building recognition in mobile terminals .

Key words: Urban building recognition    SIFT    Local Search    Line features matching    Sky-line of construction
收稿日期: 2011-04-11 出版日期: 2013-01-23
:  TP 391  
通讯作者: 范海生(1973-),男,山东菏泽人,博士,主要从事遥感与地理信息系统、遥感云服务等方面的研究。Email:haisheng.fan@gmail.com。    
作者简介: 李松霖(1981-),男,海南海口人,硕士研究生,主要从事图像处理和卫星导航技术应用等方面的研究。Email:leesonglin@gmail.com。
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:

李松霖,范海生,陈秀万. 基于特征线匹配的城市建筑物识别方法研究[J]. 遥感技术与应用, 2012, 27(2): 190-196.

Li Songlin,Fan Haisheng,Chen Xiuwan. Research of Urban Building Recognition Method based on Line Features Matching. Remote Sensing Technology and Application, 2012, 27(2): 190-196.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2012.2.190        http://www.rsta.ac.cn/CN/Y2012/V27/I2/190

[1]Yeh T,Lee J J,Darrell T.Fast Concurrent Object Localization and Recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition,Miami,2009:280-287.
[2]Lindeberg T.Scale-space Theory:A Basic Tool for Analysing Structures at Different Scales[J].Journal of Applied Statistics,1994,21(1&2):225-270.
[3]Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal on Computer Vision,2004,60(2):91-110.
[4]Feng Jingkuai.City Geographical Position Recognition System base on SIFT Feature Matching Algorithm[J].Computer & Telecommunication,2009,8:53-55.[冯镜蒯.基于SIFT特征匹配算法的城市地点识别系统[J].电脑与电信,2009,8:53-55.]
[5]Jin Taisong,Li Cuihua,Wei Benjie.Approach to Building Recognition[J].Computer Engineering and Application,2009,42(33):1-3.[金泰松,李翠华,魏本杰.一种建筑物目标识别方法[J].计算机工程与应用,2009,42(33):1-3.]
[6]Jin Taisong,Ye Congyin,Li Cuihua,et al.Approach to Building Recognition in Complex Scenes[J].Computer Engineering,2007,33(6):198-200.[金泰松,叶聪颖,李翠华,等.一种复杂场景下建筑目标识别方法[J].计算机工程,2007,33(6):198-200.]
[7]Wang Zheshen,Li Cuihua.Improved Classical Hough Transform Applied to Building Detection and Recognition[J].Journal of Image and Graphics,2005,10(4):463-467.[汪哲慎,李翠华.基于改进Hough变换的建筑目标搜索与识别[J].中国图象图形学报,2005,10(4):463-467.]
[8]Wang Junqiu,Zha Hongbin.Combining Interest Points and Edges for Building and Object Recognition[J].Journal of Computer Aided Design & Computer Graphics,2006,18(8):1257-1263.[王君秋,查红彬.结合兴趣点和边缘的建筑物和物体识别方法[J].计算机辅助设计与图形学学报,2006,18(8):1257-1263.]
[9]Beveridge J R.Local Search Algorithms for Geometric Object Recognition;Optimal Correspondence and Pose[D].Amherst:University of Massachusetts,1993.
[10]Canny J.A Computational Approach to Edge Detection[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1996,8:679-698.

[1] 宋耀鑫,张丹丹,唐伶俐,李传荣,马灵玲. 基于ASIFT算法的低重叠度无人机影像拼接方法[J]. 遥感技术与应用, 2015, 30(4): 725-730.