基于图卷积神经网络的道路网匹配

doi:10.13474/j.cnki.11-2246.2023.0353

测绘通报 ›› 2023, Vol. 0 ›› Issue (12): 19-24,44.doi: 10.13474/j.cnki.11-2246.2023.0353

• 道路与智能交通驾驶 • 上一篇

基于图卷积神经网络的道路网匹配

齐杰^1,2,3, 王中辉^1,2,3, 李驿言^1,2,3

1. 兰州交通大学测绘与地理信息学院, 甘肃兰州 730070;
2. 地理国情监测技术应用国家地方联合工程研究中心, 甘肃兰州 730070;
3. 甘肃省地理国情监测工程实验室, 甘肃兰州 730070

收稿日期:2023-04-10 发布日期:2024-01-08
通讯作者: 王中辉。E-mail:1449041349@qq.com
作者简介:齐杰(1998-),男,硕士,研究方向为空间相似与制图综合。E-mail:1014655296@qq.com
基金资助:
国家自然科学基金(41861060;41561090);兰州交通大学优秀平台(201806);中央引导地方科技发展资金(YDZX20216200001803)

Road network matching based on graph convolutional neural network

QI Jie^1,2,3, WANG Zhonghui^1,2,3, LI Yiyan^1,2,3

1. Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, China;
2. National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring, Lanzhou 730070, China;
3. Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou 730070, China

Received:2023-04-10 Published:2024-01-08

摘要/Abstract

摘要： 针对当前道路网匹配方法中权重关系和匹配阈值的确定主观性强、容易产生匹配误差等问题,提出了一种结合图卷积神经网络的道路网匹配方法。首先,选取长度、方向、距离、拓扑4个相似性度量因子作为道路网匹配模型的特征因子;然后,将待匹配道路转化为以道路为节点、道路的连接关系为边的对偶图的图结构,即把道路网匹配问题转化为节点分类的问题;最后,通过搭建图卷积神经网络实现道路网的匹配。试验结果表明,与传统方法相比,该方法的匹配准确率、召回率及F值均得到大幅提升,能够有效解决道路网匹配问题。

关键词: 道路网匹配, 图卷积神经网络, 深度学习

Abstract: The current road network matching methods are highly subjective in determining the weighted relations and matching threshold and prone to matching errors. Therefore, a road network matching method combining graph convolutional neural network is proposed. First, four similarity measure factors of length, direction, distance and topology are selected as the feature factors of the road network matching model. Then the roads to be matched are transformed into a dual graph with roads as nodes and road connection relations as edges, thus to match road network through node classification. Finally, the road network matching is realized by building a graph convolutional neural network. The results show that the matching accuracy, recall rate, and F-value of this method are greatly improved compared with the traditional methods, and it can effectively solve the road network matching problem.

Key words: road network matching, graph convolutional neural network, deep learning

中图分类号:

P208

齐杰, 王中辉, 李驿言. 基于图卷积神经网络的道路网匹配[J]. 测绘通报, 2023, 0(12): 19-24,44.

QI Jie, WANG Zhonghui, LI Yiyan. Road network matching based on graph convolutional neural network[J]. Bulletin of Surveying and Mapping, 2023, 0(12): 19-24,44.

参考文献

[1] 郭宁宁. 矢量道路数据的自动匹配与变化检测研究[D]. 南京: 南京师范大学, 2017.
[2] 吴冰娇,王中辉,杨飞. 用于多尺度道路网匹配的语义相似性计算模型[J].测绘科学,2022,47(3):166-173.
[3] 郭小菊,陈俊杰. 基于地理本体的同名实体匹配技术研究[J]. 计算机应用与软件,2015,32(2): 66-68.
[4] YANG Xue,TANG Luliang,STEWART K,et al. Automatic change detection in lane-level road networks using GPS trajectories[J]. International Journal of Geographical Information Science,2018,32(3): 601-621.
[5] 安晓亚,刘平芝,杨云,等. 一种线状要素几何相似性度量方法及其应用[J]. 武汉大学学报(信息科学版),2015,40(9): 1225-1229.
[6] 陈玉敏,龚健雅,史文中. 多尺度道路网的距离匹配算法研究[J]. 测绘学报,2007,36(1): 84-90.
[7] SAALFELD A. Conflation automated map compilation[J]. International Journal of Geographical Information Systems,1988,2(3): 217-228.
[8] 王米琪,艾廷华,晏雄锋,等. 图卷积网络模型识别道路正交网格模式[J]. 武汉大学学报(信息科学版),2020,45(12): 1960-1969.
[9] 张康,郑静,沈婕,等. 图卷积网络在道路网选取中的应用[J]. 测绘科学,2021,46(2): 165-170.
[10] BRUNA J,ZAREMBA W,SZLAM A,et al. Spectral networks and locally connected networks on graphs[C]//Proceedings of 2013 International Conference on Learning Representations.Scottsdale:[s.n.],2013.
[11] DEFFERRARD M,BRESSON X,VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. New York: ACM Press,2016: 3844-3852.
[12] KIPF T N,WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of 2017 International Commission for Labor Rights(ICLR). Toulon:[s.n.],2017.
[13] 余梦娟. 基于Voronoi图的多尺度道路网匹配方法研究[D]. 南昌: 江西师范大学,2017.
[14] ZHANG M,SHI W,MENG L.A generic matching algorithm for line networks of different resolutions[C]//Proceedings of 2005 Ica Workshop on Generalisation & Multiple Representation A Corua. Spain: [s.n.],2005.
[15] 张猛,吴巧丽,钱海忠. 一种适用于多源道路网自动匹配的通用算法[J]. 测绘科学技术学报,2018,35(1): 82-86.
[16] FAN Hongchao,YANG Bisheng,ZIPF A,et al. A polygon-based approach for matching OpenStreetMap Road networks with regional transit authority data[J]. International Journal of Geographical Information Science,2016,30(4): 748-764.

基于图卷积神经网络的道路网匹配

Road network matching based on graph convolutional neural network

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	魏德宏, 禤键豪, 杨嘉伟, 张兴福, 余旭. 基于深度BP/ELMAN神经网络的山区GNSS高程转换精度分析[J]. 测绘通报, 2023, 0(9): 113-116,143.
[2]	张宝安, 高小龙, 金仔燕, 马兰花. 甘肃省地表要素遥感解译样本库建设与应用[J]. 测绘通报, 2023, 0(9): 144-149.
[3]	胡荣明, 李鑫, 竞霞, 武建强, 魏青博. YOLOv7在探地雷达B-Scan图像解译中的应用[J]. 测绘通报, 2023, 0(8): 29-33.
[4]	周宝定, 谢沛瑶, 郭文浩, 毛庆洲. 基于激光点云灰度图像的隧道渗水病害检测[J]. 测绘通报, 2023, 0(8): 34-39,90.
[5]	张戬, 高雅. 深度学习遥感影像解译技术在耕地保护中的应用[J]. 测绘通报, 2023, 0(8): 142-145.
[6]	杨盈, 邱芹军, 谢忠, 田苗, 郑诗语, 郑帅. 人在回路学习增强的地理命名实体识别[J]. 测绘通报, 2023, 0(8): 155-160,177.
[7]	钟静, 孙杰, 赖祖龙, 谌一夫. ICESat-2与Sentinel-2数据融合的深度学习浅滩水深测量[J]. 测绘通报, 2023, 0(7): 39-43.
[8]	沈鑫甦, 嵇灵. 面向遥感地类变化检测的U型深度学习神经网络改进方法[J]. 测绘通报, 2023, 0(6): 93-97,103.
[9]	陈桥驿, 闫宇飞, 黄永芳. 融合面向对象和深度置信网络的农村建筑物信息提取[J]. 测绘通报, 2023, 0(6): 134-137.
[10]	王丽梅, 王延正. 基于高分辨率遥感影像的建筑物提取[J]. 测绘通报, 2023, 0(6): 180-183.
[11]	李心媛, 贺智, 楼桉君, 肖曼. 双线性图卷积网络的环南海地区湿地遥感分类[J]. 测绘通报, 2023, 0(5): 44-50.
[12]	蔡军, 温日强, 江伟, 严娇, 卢丽娟. 传统村落航拍图像中民族建筑识别的DeepLabV3+改进算法[J]. 测绘通报, 2023, 0(4): 49-53.
[13]	齐建伟, 王伟峰, 张乐, 王光彦. 基于改进DeepLabV3+算法的遥感影像建筑物变化检测[J]. 测绘通报, 2023, 0(4): 145-149.
[14]	佘佐明, 申勇智, 宋剑虹, 向玉瑨. 利用经典CNN网络方法构建贵阳市道路要素遥感影像自动提取模型[J]. 测绘通报, 2023, 0(4): 177-182.
[15]	王本礼, 王也, 唐先龙, 董胜光. 遥感影像变化图斑智能化提取平台研发与应用[J]. 测绘通报, 2023, 0(2): 150-154.