多源道路网数据自动匹配算法研究

The growing demand on geospatial services requires an emphasized study on geo-information from various sources covering the same geographic space. Data matching, which aims at establishing logical connections (linkages) between corresponding objects or object parts in two comparable datasets, is one of the fundamental measures that helps make different datasets interoperable. A road network serves in many cases as the geometric and functional backbone in a comprehensive digital landscape model. Hence, street matching has been intensively and extensively researched during the last decade. Buffer Growing(BG) and Iterative Closest Point (ICP) are two popular matching algorithms that have been most frequently cited in literature so far. A majority of the existing matching approaches based on these two algorithms or their combination reveal a high matching rate and efficiency on certain data types of selected test areas. However, the problem of uncertain matching remains either in areas where the context is too complex or when one of the datasets contains little or no meaningful semantic information. Under the assumption that if more context information could be involved, the matching result would be better, this research is devoted to a new automatci matching algorithm based on network comparisons.Different to BG and ICP, the network-based matching algorithm is able to make use of topologic information more conveniently and sufficiently, which allows a context-related topologic analysis, thus helps to improve the results of geometric or semantic matching. Furthermore, to make the alogrithm more robust and generic, several methodlogies of "pattern recognition" and "data generalization" will be implemented in this matching approach. In addition,"cloud computing" technologies will be tried as well, so that a more speedy matching algorithm could be desirable. In general, this research addresses an automatic matching approach with fresh ideas and theories. Much more than a significant matching prototype, the proposed matching approach would have the potentialities to be extended to a commercial software production.

随着GIS技术的不断发展，一个不可避免的新课题摆在了我们面前，即"多源空间数据的匹配与融合"。作为其中的一个重要分支，"多源道路网数据自动匹配算法"的研究始于上个世纪90年代中期，至今已取得了许多成果，开发出诸如BG、ICP等匹配算法和模型。本课题将对传统BG、ICP算法的优缺点进行全面的研究分析，并拟在此基础上创建新的基于"网络要素"比对的匹配算法，该算法能够更加全面的考虑道路间的拓扑关系与上下文关系，从而期望在匹配的成功率和准确率方面能有所突破。同时，本课题将设法在匹配运算中引入"模式识别"和"地图综合"的新思维与新方法，以便使该算法更具普遍性与一般性。此外，本课题还将尝试使用"云计算技术"，为匹配海量道路网数据的快速运算，甚至是实时运算提供必要的技术支撑。简言之，本课题旨在研究新的理论算法，开发相应的软件产品，将"多源道路网数据自动匹配算法"的研究推向新的高度。

随着GIS技术的不断发展，一个不可避免的新课题摆在了我们面前，即“多源空间数据的匹配与融合”。作为该领域的一个重要分支，多源道路网数据自动匹配算法的研究也变得日趋重要。鉴于空间数据的海量性，我们很难依靠手动的方法来实现空间数据的匹配与融合。因此，高自动化的匹配算法便成了研究重点。. 本课题对传统BG、ICP算法的优缺点进行了全面的研究分析，并在此基础上创建了一种新的基于“网络要素”比对的匹配算法，并将其命名为“限定笔划”算法。该算法能够更加全面的考虑道路间的拓扑关系与上下文信息关系，从而极大的提高了匹配运算的成功率和准确率。同时，本课题还将“模式识别”和“地图综合”的新思维与新方法引入到了道路网的匹配运算中，从而使该算法更具普遍性与一般性，可适用于多种不同的道路网数据。此外，本课题还建立了道路网数据自动融合的算法模型，实现了道路网数据在不同空间数据集间的自动传递与无缝连接。. 本课题研究了新的理论算法，开发了相应的软件原型。在海量数据的测试中，该算法同时具有匹配成功率高、准确率高、运算速度快以及通用性强等多项优点。鉴于此，该算法被应用到了三个实际的数据加工生产项目之中，均出色完成了项目的既定目标任务，将“多源道路网自动融合”的研究与应用推向了新的高度，完成了本课题预期的研究目标。