采用主成分分析的面状居民地匹配指标简化方法
|
摘要
现有多源居民地匹配中存在众多的面要素度量指标,若全部进行考虑,则增加了匹配的复杂性;若只考虑部分指标,则可能造成匹配信息的缺失,影响匹配结果。针对这一问题,本文提出一种采用主成分分析方法的面状居民地匹配方法。借鉴主成分分析法中降维的思想,对居民地各项度量指标进行定性定量分析,通过科学计算确定面要素匹配综合指标,用较少的新指标代替原来较多的相似性指标,进而根据获得的整体相似性评价指标进行居民地匹配。实验分析表明,本文方法简化了匹配过程中众多的相似性指标,降低了匹配复杂性和不确定性,避免了各相似权值确定较为随意的问题,有效提高了匹配效率和正确率。
Existing habitation matching methods mostly use lots of matching indicators,it will increase the complexity of matching if consider all,but if consider part of the indicator,the matching information will miss and impact matching results. In response to these problems,A habitation matching indicators simplify method by using principal component analysis is proposed. Based on the principal component analysis idea of principal component analysis,analysis the habitation indicators metrics for qualitative and quantitative,through scientific calculation to determine comprehensive indicators of surface matching elements,with fewer new indicators instead of more original similar indicators,then according to obtain the overall similarity evaluation indicators of habitation to match. Experiments show that method simplifies the matching process in many similarity metrics,can reduce the matching complexity and uncertainty,to avoid the similar weights are free of problems,effectively improve the matching efficiency and accuracy.
Existing habitation matching methods mostly use lots of matching indicators,it will increase the complexity of matching if consider all,but if consider part of the indicator,the matching information will miss and impact matching results. In response to these problems,A habitation matching indicators simplify method by using principal component analysis is proposed. Based on the principal component analysis idea of principal component analysis,analysis the habitation indicators metrics for qualitative and quantitative,through scientific calculation to determine comprehensive indicators of surface matching elements,with fewer new indicators instead of more original similar indicators,then according to obtain the overall similarity evaluation indicators of habitation to match. Experiments show that method simplifies the matching process in many similarity metrics,can reduce the matching complexity and uncertainty,to avoid the similar weights are free of problems,effectively improve the matching efficiency and accuracy.
引文
[1]Yuan S,Tao C.Development of Conflation Components[C]//Proceedings of Geoinformatics 1999 Conference.Ann Arbor,1999.
[2]Masuyama A.Methods for Detecting Apparent Differences Between Spatial Tessellations at Different Time Points[J].International Journal of Geographical Information Science,2006,20(6):633-648.
[3]Von G.G,Sester M.Change Detection and Integration of Topographic Updates from ATKIS to Geoscientific Data Sets[C]//International Conference on Next Generation Geospatial Information.Boston,2003.
[4]Van Wijngarden F,Van Putten J,Van Oosterom,et al.Map Integration-Update Propagation In A Multi-Source Environment[C]//Proceedings of 5th ACM International Workshop on Advances In Geographic Information Systems.Las Vegas,Nevada,United States,1997.
[5]Winter S.Location-based similarity measures of regions[C]//International Archives of Photogrammety and Remote Sensing,ISPRS Commission IV Symposium on GISBetween Visions and Applications.Stuttgart,Germany,1998.
[6]吴建华,付仲良.数据更新中要素变化检测与匹配方法[J].计算机应用,2008,28(6):1612-1615.
[7]章莉萍,郭庆胜,孙艳.相邻比例尺地形图之间居民地要素匹配方法研究[J].武汉大学学报:信息科学版,2008,33(6):604-607.
[8]郭黎,郑海鹰,王豪.面状矢量空间数据匹配技术研究[J].海洋测绘,2009,29(3):12-15.
[9]付仲良,邵世维,童春芽.基于正切空间的多尺度面实体形状匹配[J].计算机工程,2010,36(17):216-220.
[10]艾廷华,师赟,李精忠.基于形状相似性识别的空间查询[J].测绘学报,2009,38(4):356-362.
[11]Liao S.X,Pawlak M.On Image Analysis by Moments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(3):254-266.
[12]郝燕玲,唐文静,赵玉新,等.基于空间相似性的面实体匹配算法研究[J].测绘学报,2008,37(4):501-506.
[13]郭黎,崔铁军,郑海鹰,等.基于空间方向相似性的面状矢量空间数据匹配算法[J].测绘科学技术学报,2008,25(5):380-382.
[14]黄智深,钱海忠,王骁,等.基于降维技术的面状居民地匹配方法[J].测绘科学技术学报,2012,29(1):75-78.
[15]黄智深,钱海忠,郭敏,等.面状居民地匹配骨架线傅里叶变化方法[J].测绘学报,2013,42(6):913-921.
[16]王骁,钱海忠,何海威,等.利用空白区域骨架线网眼匹配多源面状居民地[J].测绘学报,2015,44(8):927-935.
[17]邵世维.基于几何特征的多尺度矢量面状实体匹配方法研究与应用[D].武汉:武汉大学,2011.
[18]王晓峰,黄德双,杜吉祥等.叶片图像特征提取与识别技术的研究[J].计算机工程与应用,2006,42(3):190-193
[19]徐建华.现代地理学中的数学方法[M].北京:高等教育出版社,2002.
[20]华一新,吴升,赵军喜.地理信息系统原理与方法[M].北京:解放军出版社,2000.
[2]Masuyama A.Methods for Detecting Apparent Differences Between Spatial Tessellations at Different Time Points[J].International Journal of Geographical Information Science,2006,20(6):633-648.
[3]Von G.G,Sester M.Change Detection and Integration of Topographic Updates from ATKIS to Geoscientific Data Sets[C]//International Conference on Next Generation Geospatial Information.Boston,2003.
[4]Van Wijngarden F,Van Putten J,Van Oosterom,et al.Map Integration-Update Propagation In A Multi-Source Environment[C]//Proceedings of 5th ACM International Workshop on Advances In Geographic Information Systems.Las Vegas,Nevada,United States,1997.
[5]Winter S.Location-based similarity measures of regions[C]//International Archives of Photogrammety and Remote Sensing,ISPRS Commission IV Symposium on GISBetween Visions and Applications.Stuttgart,Germany,1998.
[6]吴建华,付仲良.数据更新中要素变化检测与匹配方法[J].计算机应用,2008,28(6):1612-1615.
[7]章莉萍,郭庆胜,孙艳.相邻比例尺地形图之间居民地要素匹配方法研究[J].武汉大学学报:信息科学版,2008,33(6):604-607.
[8]郭黎,郑海鹰,王豪.面状矢量空间数据匹配技术研究[J].海洋测绘,2009,29(3):12-15.
[9]付仲良,邵世维,童春芽.基于正切空间的多尺度面实体形状匹配[J].计算机工程,2010,36(17):216-220.
[10]艾廷华,师赟,李精忠.基于形状相似性识别的空间查询[J].测绘学报,2009,38(4):356-362.
[11]Liao S.X,Pawlak M.On Image Analysis by Moments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(3):254-266.
[12]郝燕玲,唐文静,赵玉新,等.基于空间相似性的面实体匹配算法研究[J].测绘学报,2008,37(4):501-506.
[13]郭黎,崔铁军,郑海鹰,等.基于空间方向相似性的面状矢量空间数据匹配算法[J].测绘科学技术学报,2008,25(5):380-382.
[14]黄智深,钱海忠,王骁,等.基于降维技术的面状居民地匹配方法[J].测绘科学技术学报,2012,29(1):75-78.
[15]黄智深,钱海忠,郭敏,等.面状居民地匹配骨架线傅里叶变化方法[J].测绘学报,2013,42(6):913-921.
[16]王骁,钱海忠,何海威,等.利用空白区域骨架线网眼匹配多源面状居民地[J].测绘学报,2015,44(8):927-935.
[17]邵世维.基于几何特征的多尺度矢量面状实体匹配方法研究与应用[D].武汉:武汉大学,2011.
[18]王晓峰,黄德双,杜吉祥等.叶片图像特征提取与识别技术的研究[J].计算机工程与应用,2006,42(3):190-193
[19]徐建华.现代地理学中的数学方法[M].北京:高等教育出版社,2002.
[20]华一新,吴升,赵军喜.地理信息系统原理与方法[M].北京:解放军出版社,2000.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |