摘要
stroke将多条道路段视为一个整体,在降低道路复杂性的同时增强了道路网的连通性,是道路网综合、拓扑分析和模式识别等的基础。已有研究主要按照“良好连续性”原则进行stroke的构建,考虑到了道路的几何特征,但是路段是具有自身属性和现实功能的客观实体,stroke的生成还应该遵循路段的重要程度相近原则。因此,本文提出了一种基于几何、拓扑及语义相似的道路网stroke生成方法。首先,根据语义信息在未处理道路中确定起始路段;其次,基于道路的特征因子生成路段间的相似矩阵;最后,根据路段间的相似度,选择候选路段中与起始路段的相似度最接近的路段进行连接。实验表明,本文方法不仅可以构建出视觉上自然延伸的stroke,而且构建的结果还在一定程度上满足了功能一致性。与已有方法相比,引入相似关系生成的stroke结果可以更好地反映道路段的现实连通情况。
Owing to regarding multiple single roads as a whole,the stroke reduces the complexity of roads and enhances the connectivity of road network,which lays a foundation for performing road network generalization,topology analysis and pattern recognition.During the construction of stroke,general studies follow the principle of good continuation and take the geometric features of the road into account,however the road segments are an objective entity which have attributes and practical functions.The generation of stroke should also follow the principle of similar importance of the road segments.Therefore,this paper proposes a road network stroke generation method based on geometric,topological,and semantic similarity.Firstly,the starting road segment is determined in the unprocessed road according to the semantic information.Secondly,the similarity matrix between road segments is generated based on the characteristic factors of segments.Finally,according to the similarity between segments,select the closest similarity between the candidate segments and the starting segment to connect.The experimental results show that the stroke construct by the proposed method can not only keep good continuation,but also fit the functional consistency to a certain extent.Compared with the existing methods,the stroke results generated by introducing the similarity relationship can better reflect the actual connectivity of road sections.
作者
禄小敏
闫浩文
刘文蕊
叶云会
LU Xiaomin;YAN Haowen;LIU Wenrui;YE Yunhui(Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China;National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring,Lanzhou 730070,China;Gansu Provincial Engineering Laboratory for National Geographic State Monitoring,Lanzhou 730070,China)
出处
《测绘科学技术学报》
2025年第5期479-485,共7页
Journal of Geomatics Science and Technology
基金
国家自然科学基金项目(42471476,42161066)
甘肃省自然科学基金重点项目(24JRRA224)。
