利用属性图的遥感数据与GIS数据松弛标号匹配Relaxing labeling matching for remote sensing image and GIS data based on attributed graph
娄博,耿则勋,魏小峰,沈忱
摘要(Abstract)：
本文提出一种基于图形匹配来配准影像和地图的方法。该方法将道路网表示成图形,通过对两个图形进行最优匹配来实现影像和地图的配准;同时采用一种整体相容函数来量测两个图形的整体对应优度,并通过连续松弛标号来优化此过程。该方法对平移、旋转变化和尺度变化具有不变性(通过利用合适的属性),同时网络结构的利用降低了非精确匹配过程中的搜索空间的不确定性;该方法不需要用户自定义阈值来调整局部匹配。实验结果表明该方法具有较高的可靠性。
关键词(KeyWords)： 遥感影像;GIS数据;图形匹配;道路网;松弛标号匹配
基金项目(Foundation):
作者(Author): 娄博,耿则勋,魏小峰,沈忱
DOI: 10.16251/j.cnki.1009-2307.2014.07.023
参考文献(References)：
- [1]刘志青,郭海涛,张保明.一种基于直线特征的遥感影像和GIS数据自动整体配准方法[J].测绘科学技术学报,2011,28(2):129-133.
- [2]C Drewniok,K Rohr.Automatic exterior orientation of aerial images in urban environment[J].International Archives of Photogrammetry&Remote Sensing,1996,30:146-152.
- [3]K Rohr.Landmark-based image analysis:using geometric and intensity models[M].Dordrecht,Boston:Kluwer Academic Publishers,2001.
- [4]W Schickler.Feature matching for outer orientation of single images using 3-D wireframe control points[J].International Archives of Photogrammetry&Remote Sensing,1996,29.
- [5]I Dowman.Automating image registration and absolute orientation:solutions and problems[J].Photogrammetric Record,1998,16(91):5-18.
- [6]H Hild,N Haala,D Fritsch.A strategy for automatic image to map registration[J].International Archives of Photogrammetry and Remote Sensing,2000,33:313-321.
- [7]R A Hummel,S W Zucker.On the foundations of relaxation labeling processes[J].IEEE PAMI,1983,5(3):267-287.
- [8]Rosenfeld A,Hummel R,Zucker S.Scene labeling by relaxation operations[C]//IEEE Trans.Syst.ManCybern:1976,6(6):420-433.
- [9]Mohammed J,Hummel R,Zucker S.A feasible direction operator for relaxation methods[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI),1983,5(3):330-332.
- [10]柳林,等.实时高精度地图匹配技术的研究与实现[J].测绘科学,2010,35(5).
- [11]吕长青,王忠武,钱少猛.混合像元分解模型综述[J].遥感信息,2013(3):55-58.