Relaxation Labelling Matching for Multi-scale Residential Datasets Based on Neighboring Patterns
-
摘要: 空间目标匹配是实现多源空间信息融合、空间对象变化检测与动态更新的重要前提。针对多比例尺居民地匹配问题，提出了一种基于邻近模式的松弛迭代匹配方法。该方法首先利用缓冲区分析与空间邻近关系检测候选匹配目标与邻近模式，同时计算候选匹配目标或邻近模式间的几何相似性得到初始匹配概率矩阵；然后对邻近候选匹配对进行上下文兼容性建模，利用松弛迭代方法求解多比例尺居民地的最优匹配模型，选取匹配概率最大并满足上下文一致的候选匹配目标或邻近模式为最终匹配结果。实验结果表明，所提出的多比例尺居民地匹配方法具有较高的匹配精度，能有效克服形状轮廓同质化与非均匀性偏差问题，并准确识别1:M、M:N的复杂匹配关系。Abstract: This paper proposes a relaxation labelling matching approach for multi-scale residential datasets based on neighboring patterns. Firstly, we detect the candidate matching objects and neighboring patterns by buffering analysis and spatial neighboring relations. Secondly, the geometric similarities of candidate matching objects or neighboring patterns are calculated to initialize the matching matrix that contains 1:1, 1:M and M:N relations. After that, the contextual information of neighborhood objects or patterns are explored to heuristically update the matching matrix to achieve a global consistency. The matching pairs with maximum probabilities are finally selected after context consistency detection. The experimental results and contrast analysis show that our method obtains high correct matching rates, efficiently overcomes the problems of shape homogeneity and uneven deviation, and can correctly identify complex 1:M and M:N matching objects in multi-scale residential datasets.
-
-
![]()
图 5 模拟居民地数据的匹配结果对比
Figure 5. Comparison of Matching Results of Simulated Residential Data
![]()
图 6 中国西安市和美国达拉斯市实验区数据匹配结果
Figure 6. Matching Results of Test Datasets of Xi'an and Dallas
表 1 实验数据统计与参数设置
Table 1 Experimental Data Statistics and Parameter Settings
实验数据 数据S/面目标数目 数据T/面目标数目 位置阈值Tpos 方向阈值Tdir 面积阈值Tarea 形状阈值Tshp 迭代阈值α 模拟数据 小比例尺/25 大比例尺/42 0.75 0.95 0.80 0.75 0.000 5 中国西安市数据 1:2.5万/83 1:2万/118 0.70 0.95 0.65 0.72 0.000 5 美国达拉斯市数据 OpenStreetMap/83 网络数据/80 0.87 0.93 0.90 0.87 0.000 5 注：美国达拉斯市数据的下载地址分别为：OpenStreetMap为http://download.geofabrik.de/north-america/us/texas.html；网络数据为https://gis.dallascityhall.com/shapezip.htm。 
下载: 导出CSV
表 2 实验精度评价/%
Table 2 Statistics of Precision, Recall and F Value/%
数据 方法 准确率P 召回率R F值 模拟数据 文献[12]方法
本文方法100
10068.57
10081.35
100中国西安市数据 本文方法 93.56 91.47 92.5 美国达拉斯市数据 本文方法 98.12 95.45 96.93
下载: 导出CSV
表 3 邻近模式的匹配示例
Table 3 Matching Examples of Neighboring Pattern Combination
组合示例 数据T 候选匹配组合 匹配概率 示例1
A1 {a1} 0.011 {a1, a2} 0.046 9 { a1, a2, a3} 0.138 { a1, a2, a3, a4} 0.218 示例2
B1 {b1} 0.058 5 {b2} 0.142 4 {b1, b2} 0.308 {b1, b2, b3} 0.051 B2 {b1} 0.070 {b3} 0.130 {b1, b3} 0.290 {b1, b2, b3} 0.055
下载: 导出CSV
-
[1] 李清泉, 李德仁.大数据GIS[J].武汉大学学报·信息科学版, 2014, 39(6):641-644 http://ch.whu.edu.cn/CN/abstract/abstract3000.shtml Li Qingquan. Li Deren. Big Data GIS[J]. Geomatics and Information Science of Wuhan University, 2014, 39(6):641-644 http://ch.whu.edu.cn/CN/abstract/abstract3000.shtml
[2] Jiang B. Volunteered Geographic Information and Computational Geography: New Perspectives[M]//Sui D, Elwood S, Goodchild M. Crowdsourcing Geographic Knowledge. Dordrecht: Springer, 2013
[3] 陈军, 李志林, 蒋捷, 等.基础地理数据库的持续更新问题[J].地理信息世界, 2004, 2(5):1-5 http://www.cnki.com.cn/Article/CJFDTotal-WHCH201404003.htm Chen Jun, Li Zhilin, Jiang Jie, et al. Key Issues of Continuous Updating of Geo-spatial Databases[J]. Geomatics World, 2004, 2(5):1-5 http://www.cnki.com.cn/Article/CJFDTotal-WHCH201404003.htm
[4] 张云菲, 杨必胜, 栾学晨.利用概率松弛法的城市路网自动匹配[J].测绘学报, 2012, 41(6):933-939 http://www.docin.com/p-1473550349.html Zhang Yunfei, Yang Bisheng, Luan Xuechen. Automated Matching Urban Road Networks Using Pro-babilistic Relaxation[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(6):933-939 http://www.docin.com/p-1473550349.html
[5] 张桥平, 李德仁, 龚健雅.城市地图数据库面实体匹配技术[J].遥感学报, 2004, 8(2):107-112 doi: 10.11834/jrs.20040203 Zhang Qiaoping, Li Deren, Gong Jianya. Areal Feature Matching Among Urban Geographic Databases[J]. Journal of Remote Sensing, 2004, 8(2):107-112 doi: 10.11834/jrs.20040203
[6] 赵东保, 盛业华, 张卡.利用几何矩和叠置分析进行多尺度面要素自动匹配[J].武汉大学学报·信息科学版, 2011, 36(11):1371-1375 http://ch.whu.edu.cn/CN/abstract/abstract719.shtml Zhao Dongbao, Sheng Yehua, Zhang Ka. An Algorithm for Multi-Scale One-to-many Areal Feature Matching Based on Geometry Moments and Overly Analysis[J]. Geomatics and Information Science of Wuhan University, 2011, 36(11):1371-1375 http://ch.whu.edu.cn/CN/abstract/abstract719.shtml
[7] 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 doi: 10.3321/j.issn:1001-1595.2008.04.017 Hao Yanling, Tang Wenjing, Zhao Yuxin, et al. Areal Feature Matching Algorithm Based on Spatial Similarity[J]. Acta Geodaetica et Cartographica Sinica, 2008, 37(4):501-506 doi: 10.3321/j.issn:1001-1595.2008.04.017
[8] Fan H, Zipf A, Fu Q, et al. Quality Assessment for Building Footprints Data on OpenStreetMap[J]. International Journal of Geographical Information Science, 2014, 28(4):700-719 doi: 10.1080/13658816.2013.867495
[9] Ai T, Cheng X, Liu P, et al. A Shape Analysis and Template Matching of Building Features by the Fourier Transform Method[J]. Computers, Environment and Urban Systems, 2013, 41(5):219-233 http://www.sciencedirect.com/science/article/pii/S019897151300063X
[10] 许俊奎, 武芳, 钱海忠, 等.一种空间关系相似性约束的居民地匹配算法[J].武汉大学学报·信息科学版, 2013, 38(4):484-488 http://ch.whu.edu.cn/CN/abstract/abstract775.shtml Xu Junkui, Wu Fang, Qian Haizhong, et al. Settlement Matching Algorithm Using Spatial Similarity Relations as Constraints[J]. Geomatics and Information Science of Wuhan University, 2013, 38(4):484-488 http://ch.whu.edu.cn/CN/abstract/abstract775.shtml
[11] 焦洋洋, 王卉, 翟仁健.顾及邻域相似性的面要素匹配方法[J].辽宁工程技术大学学报(自然科学版), 2013, 32(7):947-952 http://www.cqvip.com/QK/94702A/201307/1002813155.html Jiao Yangyang, Wang Hui, Zhai Renjian. Matching Method for Areal Feature Considering Context-Dependent Similarity[J]. Journal of Liaoning Technical University (Natural Science), 2013, 32(7):947-952 http://www.cqvip.com/QK/94702A/201307/1002813155.html
[12] Zhang X, Ai T, Stoter J, et al. Data Matching of Building Polygons at Multiple Map Scales Improved by Contextual Information and Relaxation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 92(6):147-163 http://adsabs.harvard.edu/abs/2014JPRS...92..147Z
[13] 胡继萍.不同比例尺面目标数据匹配方法[J].科技创新与生产力, 2016(4):89-92 http://www.cqvip.com/QK/90069X/201104/38922696.html Hu Jiping. Area Target Data Matching Method of Different Scales[J].Applied Technology, 2016(4):89-92 http://www.cqvip.com/QK/90069X/201104/38922696.html
[14] 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 http://ch.whu.edu.cn/CN/abstract/abstract1622.shtml Zhang Liping, Guo Qingsheng, Sun Yan. The Method of Matching Residential Features in Topographic Maps at Neighboring Scales[J]. Geomatics and Information Science of Wuhan University, 2008, 33(6):604-607 http://ch.whu.edu.cn/CN/abstract/abstract1622.shtml
[15] Huh Y, Kim J, Lee J, et al. Identification of Multi-scale Corresponding Object-Set Pairs Between Two Polygon Datasets with Hierarchical Co-clustering[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 88(2):60-68 https://www.sciencedirect.com/science/article/pii/S0924271613002797
[16] 许俊奎, 武芳, 朱建东, 等.相邻比例尺居民地匹配[J].武汉大学学报·信息科学版, 2014, 39(3):340-345 http://or.nsfc.gov.cn/handle/00001903-5/254508 Xu Junkui, Wu Fang, Zhu Jiandong, et al. A Multi-to-Multi Matching Algorithm Between Neighborhood Scale Settlement Data[J]. Geomatics and Information Science of Wuhan University, 2014, 39(3):340-345 http://or.nsfc.gov.cn/handle/00001903-5/254508
[17] 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 doi: 10.11947/j.AGCS.2015.20140462 Wang Xiao, Qian Haizhong, He Haiwei, et al. Matching Multi-source Areal Habitations with Ske-leton Line Mesh of Blank Region[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(8):927-935 doi: 10.11947/j.AGCS.2015.20140462
[18] Yang B, Zhang Y, Luan X. A Probabilistic Relaxation Approach for Matching Road Networks[J]. International Journal of Geographical Information Science, 2013, 27(2):319-338 doi: 10.1080/13658816.2012.683486
[19] Deng M, Liu Q, Cheng T, et al. An Adaptive Spatial Clustering Algorithm Based on Delaunay Triangulation[J]. Computers, Environment and Urban Systems, 2011, 35(4):320-332 doi: 10.1016/j.compenvurbsys.2011.02.003
[20] 张晶, 周烨, 刘瑜. SDS模型化简合并多边形的一个改进算法研究[J].中国图象图形学报, 2006, 11(7):1010-1016 doi: 10.11834/jig.200607173 Zhang Jing, Zhou Ye, Liu Yu. An Improved Algorithm for SDS Model Based Polygon Simplification and Aggregation[J]. Journal of Image and Graphics, 2006, 11(7):1010-1016 doi: 10.11834/jig.200607173
[21] Duchêne C, Bard S, Barillot X, et al. Quantitative and Qualitative Description of Building Orientation[C]. The 5th Workshop on Progress in Automated Map Generalisation, Barcelona, 2003
[22] Kim J O, Yu K, Heo J, et al. A New Method for Matching Objects in Two Different Geospatial Datasets Based on the Geographic Context[J].Computers & Geosciences, 2010, 36(9):1115-1122 http://dblp.uni-trier.de/db/journals/gandc/gandc36.html#KimYHL10
[23] Parent P, Zucker S W. Radial Projection:An Efficient Update Rule for Relaxation Labeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(8):886-889 doi: 10.1109/34.31449
-
期刊类型引用(3)
1. 周永章，陈川，张旗，王功文，肖凡，沈文杰，卞静，王亚，杨威，焦守涛，刘艳鹏，韩枫. 地质大数据分析的若干工具与应用. 大地构造与成矿学. 2020(02): 173-182 . 
百度学术
2. 王叶晨梓，杜震洪，张丰，刘仁义. 面向分片地图的多分辨率格点数据统一存取方法. 浙江大学学报(理学版). 2017(05): 584-590 . 百度学术
3. 朱建章，石强，陈凤娥，史晓丹，董泽民，秦前清. 遥感大数据研究现状与发展趋势. 中国图象图形学报. 2016(11): 1425-1439 . 百度学术
其他类型引用(6)
计量
- 文章访问数: 2398
- HTML全文浏览量: 217
- PDF下载量: 228
- 被引次数: 9
