Abstract
Homonymous entity matching is an important part of multi-source spatial data integration, automatic updating and change detection. Considering the low accuracy of existing matching methods in dealing with matching multi-scale settlement data, an algorithm based on Attributed Relational Graph (ARG) is proposed. The algorithm firstly divides two settlement scenes at different scales into blocks by small-scale road network and constructs local ARGs in each block. Then, ascertains candidate sets by merging procedures and obtains the optimal matching pairs by comparing the similarity of ARGs iteratively. Finally, the corresponding relations between settlements at large and small scales are identified. At the end of this article, a demonstration is presented and the results indicate that the proposed algorithm is capable of handling sophisticated cases.
Highlights
In the field of geographical information science, homonymous entity matching has been widely used in spatial data integration (Li Deren, 2004), maintenance and regeneration of multi-scale spatial databases (Anders K H, 2004; Volz S, 2006), spatial data confusion (Xiong D, 2004), improvement and assessment of spatial data quality (Duckham M, 2005), change detection (Masuyama A, 2006) and so on
According to the geometry types of features concerned, this matching work can be divided into three classes, point-point, line-line and area-area matching, studies about point-point and line-line matching are mature, so this paper is about area-area matching, which is focused on multi-scale settlement matching
Atsushi Masuyama shifted area-area matching to point-point matching (Atsushi Masuyama, 2006), Thomas Devogele exploited the proximity of boundaries to conduct matching (Devogele T, 2002), and other studies used overlapping rate to judge corresponding relations (Zhang Qiaoping, 2004; Zhang Liping, 2008; Goesseln G V, 2005; Ying Shen, 2009)
Summary
In the field of geographical information science, homonymous entity matching has been widely used in spatial data integration (Li Deren, 2004), maintenance and regeneration of multi-scale spatial databases (Anders K H, 2004; Volz S, 2006), spatial data confusion (Xiong D, 2004), improvement and assessment of spatial data quality (Duckham M, 2005), change detection (Masuyama A, 2006) and so on. An identical geographical entity may exhibit different forms on different maps, homonymous entity matching takes advantage of geometry, topology, semantic and other parameters to measure these different representations, distinguishes identical entities on different maps and establishes their corresponding relations. Existing studies mostly focus on matching of features at identical or similar scales and use characteristics of features as criteria. Feature characteristics are much different in multi-scale representations, which makes existing methods inapplicable. We propose a matching method based on ARG, the feature characteristics and relations between features are exploited as constraints to improve accuracy. The experiments demonstrate that this method is able to deal with complex situations such as one-many, many-many and is applicable to multi-scale representations
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
