摘要
城市道路中主要结构的识别在路网综合、多尺度路网建模、导航等方面起着关键作用。本文提出一种使用自组织映射(SOM:the Self-Organizing Map)网络来同时识别城市道路中多行道和立交桥的方法。首先计算道路网眼的几何形态特征指标,然后利用SOM对道路网眼进行分类,根据得出的网眼和道路的空间关系来提取路网中的主要结构。实验结果表明,该方法能有效地识别出城市道路中的多行道和立交桥。
The identification of major structures in urban roads plays a key role in road network integration,multi-scale road network modeling,and navigation. This paper proposes a method to use the Self-Organizing Map( SOM) to identify multiple lanes and flyovers in urban roads simultaneously. First,calculate the shape descriptors of mesh surrounded by roads,then use the SOM to classify the road mesh,and extract the major structure of the road network according to the spatial relationship between the mesh and the roads.The experimental results show that this method can effectively identify the multiple lanes and flyovers in urban roads.
引文
[1]李德仁,李清泉,杨必胜,等.3S技术与智能交通[J].武汉大学学报:信息科学版,2008,33(4):332-336.
[2]李清泉,萧世伦,方志祥,等.交通地理信息系统技术与前沿发展[M].北京:科学出版社,2012.
[3] William A Mackaness,Gordon A Mackechnie.Automating the Detection and Simplification of Junctions in Road Networks[J].GeoInformatica,1999,3(2):185-200.
[4] Guilaume Touya. A Road Network Selection Process Based on Data Enrichment and Structure Detection[J]. Transactions in GIS,2010,14(5):595-614.
[5] Bisheng Yang,Xuechen Luan,Qingquan Li. Generating hierarchical strokes from urban street networks based on spatial pattern recognition[J].International Journal of Geographical Information Science,2011,25(12):2 025-2 049.
[6]徐柱,蒙燕姿,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):125-130.
[7]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.
[8]张浩,武芳,张俊涛,等.顾及形态特征和语义信息的双线道路识别方法[J].测绘科学技术学报,2016,33(3):301-312.
[9] T Kohonen.The self-organizing map[J].Neurocomputing,1990,21(1-3):1-6.
[10]吴怡,杨琼,吴庆祥,等.基于自组织映射神经网络的VANET组网算法[J].通信学报,2011,32(12):136-144.
[11]胡云岗,陈军,李志林,等.基于网眼密度的道路选取方法[J].测绘学报,2007,36(3):351-357.
[12]栾学晨,范红超,杨必胜,等.城市道路网主干道提取的形态分析方法[J].武汉大学学报:信息科学版,2014,39(3):327-331.
[13] Bin Jiang,Lars Harrie.Selection of Streets from a Network Using Self-Organizing Maps[J]. Transactions in GIS,2010,8(3):335-350.
[14]程博艳.基于神经网络的地图建筑物要素智能综合研究[D].成都:电子科技大学,2009.
[15]刘艳,陈丽安.基于SOM的真空断路器机械故障诊断[J].电工技术学报,2017,32(5):49-52.
[16]梁斌梅.自组织特征映射神经网络的改进及应用研究[J].计算机工程与应用,2009,45(31):134-137.