| 15 | 0 | 57 |
| 下载次数 | 被引频次 | 阅读次数 |
立交桥是提高通行效率的重要设施，其结构提取对多层次道路结构建模、路网综合、导航与路径规划等具有重要意义。目前，立交桥识别与提取存在先验成本过高和样本依赖问题，为此，本文以矢量道路网络数据为研究对象，在道路网络拓扑分析与线要素形态特征分析的基础上，提出一种结合递进式道路线筛选与区域生长策略的立交桥提取方法。首先，采用DBSCAN算法识别出节点密集的立交桥候选区域；其次，通过点缓冲分析提取邻近道路线要素，并基于线形拟合参数进行递进式筛选，获取弧形匝道；最后以弧形匝道为种子，采用区域生长算法提取完整立交桥。以重庆市为实验区域进行方法验证，结果表明，该方法可有效提取多种类型立交桥，准确率达88.96%；相比现有方法对数据源依赖更低，流程更简洁高效，适用于复杂城市道路网络中立交桥结构的完整提取。
Abstract：Interchanges enable grade-separated traffic organization and efficiently connect roads of different hierarchies,playing a critical role in improving traffic efficiency.Accurate extraction of interchange structures is of great significance for multilevel road modeling,network generalization,navigation,and route planning.Existing studies on interchange identification and extraction largely rely on predefined structural template libraries or require large amounts of labeled samples to train deep learning models,resulting in high prior costs and strong dependence on training data.To address these limitations,this paper focuses on vector road network data and proposes an automatic interchange extraction method that integrates progressive road segment filtering with a region-growing strategy,based on road network topology analysis and morphological feature analysis of linear elements.First,the DBSCAN algorithm is employed to identify node-dense candidate regions of interchanges.Second,adjacent road segments are extracted using point-based buffer analysis,and progressive filtering is performed according to geometric fitting parameters to identify curved ramp segments.Finally,the curved ramps are used as seeds to extract complete interchange structures via a region-growing algorithm.Experiments conducted in Chongqing demonstrate that the proposed method can effectively extract multiple types of interchanges,achieving an overall accuracy of 88.96%.Compared with existing methods,the proposed method exhibits lower dependence on data sources and a more concise and efficient workflow,providing a practical solution for the complete extraction of interchange structures in complex urban road networks.
[1]Zhang Jiyong,Yang Yukui,Chu Lijing,et al.Deconstruction of the optimal design of urban road interchange based on the integration of smart transportation and big data[J].Computational Intelligence and Neuroscience,2022,2022:4241097.DOI:10.1155/2022/4241097.
[2]Jiao Fengwei,Xiang Longgang,Deng Yuanyuan.Automatic extraction of road interchange networks from crowdsourced trajectory data:a forward and reverse tracking approach[J].ISPRS International Journal of Geo-Information,2025,14(6):234.DOI:10.3390/ijgi14060234.
[3]Tian Xin,Shi Mengmeng,Yang Hang,et al.Research on efficient operation for compound interchange in China from an auxiliary lanes configuration aspect[J].Applied Sciences,2023,13(18):10499.DOI:10.3390/app131810499.
[4]Min Yang,Cao Minj un,Cheng Lingya,et al.Classification of urban interchange patterns using a model combining shape context descriptor and graph convolutional neural network[J].Geo-Spatial Information Science,2024,27(5):1622-1637.
[5]Wang Andong,Fang Wu,Yue Qiu,et al.A detection method for road network interchanges with the MeshCNN based on Delaunay triangulation[J].International Journal of Digital Earth,2024,17(1):2356123.DOI:10.1080/17538947.2024.2356123.
[6]刘纪平,张用川,徐胜华,等.一种顾及道路复杂度的增量路网构建方法[J].测绘学报,2019,48(4):480-488.
[7]伍阳,程亮,陈焱明,等.利用机载LiDAR数据重建大型复杂立交桥三维模型[J].地球信息科学学报,2016,18(9):1249-1258.
[8]Mackaness W A,Mackechnie G A.Automating the detection and simplification of junctions in road networks[J].GeoInformatica,1999,3(2):185-200.
[9]Scheider S,Possin J.Affordance-based individuation of junctions in open street map[J].Journal of Spatial Information Science,2012,4(1):31-56.
[10]徐柱,蒙艳姿,李志林,等.基于有向属性关系图的典型道路交叉口结构识别方法[J].测绘学报,2011,40(1):125-131.
[11]王骁,钱海忠,丁雅莉,等.采用拓扑关系与道路分类的立交桥整体识别方法[J].测绘科学技术学报,2013,30(3):324-328.
[12]龚勇,宋万忠.基于GPS数据的立交桥识别及层次判断算法[J].软件导刊,2013,12(2):61-63.
[13]陈漪.基于GPS数据的城市路网立交桥识别技术研究[D].长春:吉林大学,2011.
[14]Yang Jianting,Zhao Kongyang,Li Muzi,et al.Identifying complex junctions in a road network[J].ISPRS International Journal of Geo-Information,2020,10(1):4.DOI:10.3390/ijgi10010004.
[15]马超,孙群,陈换新,等.利用路段分类识别复杂道路交叉口[J].武汉大学学报(信息科学版),2016,41(9):1232-1237.
[16]何海威,钱海忠,谢丽敏,等.立交桥识别的CNN卷积神经网络法[J].测绘学报,2018,47(3):385-395.
[17]马京振,陈换新,朱新铭,等.利用Faster R-CNN进行立交桥自动识别与定位[J].测绘通报,2021(3):28-32.
[18]Min Yang,Jiang Chenjun,Yan Xiongfeng,et al.Detecting interchanges in road networks using a graph convolutional network approach[J].International Journal of Geographical Information Science,2022,36(6):1119-1139.
[19]李磊,王中辉.图注意力网络支持下的立交桥识别方法[J].测绘科学,2025,50(6):168-177.
[20]毛海霞.互通式立交的分类及其交通流特性分析[J].绿色环保建材,2017(5):99.
[21]沈冰.城市互通立交匝道桥梁结构设计研究[J].工程技术研究,2019,14(23):180-181.
[22]张驰,刘锴,王世法,等.高速公路互通式立体交叉出入口安全性研究综述[J].交通信息与安全,2023,41(2):1-17.
[23]Porta S,Crucitti P,Latora V.The network analysis of urban streets:a dual approach[J].Physica A-Statistical Mechanics and its Applications,2006,369(2):853-866.
[24]唐炉亮,牛乐,杨雪,等.利用轨迹大数据进行城市道路交叉口识别及结构提取[J].测绘学报,2017,46(6):770-779.
[25]Cardillo A,Scellato S,Latora V,et al.Structural properties of planar graphs of urban street patterns[J].Physical Review.E,Statistical,Nonlinear,and Soft Matter Physics,2006,73(6 Part2):066107.DOI:10.1103/PhysRevE.73.066107.
[26]Crucitti P,Latora V,Porta S,Centrality measures in spatial networks of urban streets[J].Physical review.E,Statistical,Nonlinear,and Soft Matter Physics,2006,73(3 Part 2):036125.DOI:10.1103/PhysRevE.73.036125.
[27]Zerweck L,Wesarg S,Kohlhammer J,et al.Combining seeded region growing and k-nearest neighbours for the segmentation of routinely acquired spatio-temporal image data[J].International Journal of Computer Assisted Radiology and Surgery,2023,18(11):2063-2072.
[28]Mu?oz X,Freixenet J,Cufi X,et al.Strategies for image segmentation combining region and boundary information[J].Pattern Recognition Letters,2003,24(1/3):375-392.
[29]Karami A,Johansson R.Choosing DBSCAN parameters automatically using differential evolution[J].International Journal of Computer Applications,2014,91(7):1-11.
[30]Ester M,Kriegel H P,Sander J,et al.A density-based algorithm for discovering clusters in large spatial databases with noise[C]//Proceedings of the Second International Conference on Knowledge Discovery and Data Mining.Menlo Park:AAAI Press,1996:226-231.
基本信息:
中图分类号:U495;P208
引用信息:
[1]李郑国,禄小敏,闫浩文,等.结合递进式矢量道路线筛选与区域生长策略的立交桥提取方法[J].地理与地理信息科学().
基金信息:
国家自然科学基金地区项目“深度度量学习支持下的空间线群目标相似关系计算方法”(42161066);国家自然科学基金面上项目“道路网综合结果评价的混合智能方法研究”(42471476); 甘肃省自然科学基金重点项目“混合智能支持下的地图群组目标空间分布模式识别方法”(24JRRA224)
2026-07-13
2026-07-13
2026-07-13