利用多层次网眼特征和VAE-PNN模型识别城市道路格网模式

doi:10.11947/j.AGCS.2024.20230026

测绘学报 ›› 2024, Vol. 53 ›› Issue (1): 189-198.doi: 10.11947/j.AGCS.2024.20230026

利用多层次网眼特征和VAE-PNN模型识别城市道路格网模式

张云菲, 邱泽航

长沙理工大学交通运输工程学院, 湖南长沙 410114

收稿日期:2023-02-03 修回日期:2023-11-28 发布日期:2024-02-06
通讯作者: 邱泽航 E-mail:qiuzh@stu.csust.edu.cn
作者简介:张云菲(1987-),女,博士,副教授,研究方向为时空数据分析、交通地理信息系统。E-mail:zhang.yunfei@csust.edu.cn
基金资助:
国家自然科学基金(42371474;41971421);教育部“春晖计划”合作科研项目(HZKY20220353);湖南省自然科学基金项目(2022JJ30590);湖南省科技创新计划(2021RC3099);长沙理工大学研究生实践创新项目(CLSJCX22018)

Grid patterns recognition in urban road networks using multi-level mesh features and VAE-PNN model

ZHANG Yunfei, QIU Zehang

School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China

Received:2023-02-03 Revised:2023-11-28 Published:2024-02-06
Supported by:
The National Natural Science Foundation of China (Nos. 42371474; 41971421); The “Chunhui Plan” collaborative research project of the Ministry of Education of China (No. HZKY20220353); The Natural Science Foundation of Hunan Province (No. 2022JJ30590); The Science and Technology Innovation Program of Hunan Province (No. 2021RC3099); Graduate Student Practice Innovation Project of Changsha University of Science and Technology (No. CLSJCX22018)

摘要/Abstract

摘要： 作为道路网中普遍存在的显式模式之一,格网模式蕴含了丰富的城市空间格局信息,识别道路格网模式是实现自动化、智能化地图综合的关键前提。针对现有格网模式识别方法较少考虑多层次网眼特征,存在训练样本多样性不足等问题,本文提出一种基于多层次网眼特征和VAE-PNN模型的城市道路格网模式识别方法。首先,对原始路网数据进行化简;然后,设计了内部正交函数、格网形态描述和邻域相关关系的多层次网眼特征,进而利用变分自编码器(VAE)增强训练样本多样性;最后,借助概率神经网络(PNN)模型实现道路格网模式分类识别。试验结果表明,综合考虑多层次网眼特征能够准确识别不同类型、不同形态的道路格网模式,通过VAE样本增强有效提升分类模型性能和格网模式识别精度。

关键词: 格网模式识别, 多层次网眼特征, 变分自编码器, 概率神经网络

Abstract: As one of explicit patterns widely existing in urban road network, grid patterns contain a large amount of abundant information about urban spatial pattern. Recognizing road grid patterns is also the key prerequisite for realizing automatic and intelligent map generalization. As existing methods of grid pattern recognition seldom consider multi-level mesh features and may be sensitive to the diversity of training samples, this paper proposes a novel approach for urban road grid pattern recognition based on multi-level mesh features and VAE-PNN model. Firstly, the original road network data are simplified by sophisticated DP algorithm. Then, we design a set of multi-level mesh features to measure grid patterns, including internal orthogonal function, grid shape descriptions and neighborhood correlation indicators. After that, variational auto-encoder (VAE) is used to enhance the diversity and size of training samples. Finally, probabilistic neural network (PNN) model is adopted to identify road grid patterns. The experimental results show that considering multi-level mesh features can help to identify different grid types and various grid patterns and demonstrate that introducing VAE model achieves better performance on grid pattern recognition than not.

Key words: grid patterns recognition, multi-level mesh feature, variational auto encoder, probabilistic neural network

中图分类号:

P208

张云菲, 邱泽航. 利用多层次网眼特征和VAE-PNN模型识别城市道路格网模式[J]. 测绘学报, 2024, 53(1): 189-198.

ZHANG Yunfei, QIU Zehang. Grid patterns recognition in urban road networks using multi-level mesh features and VAE-PNN model[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(1): 189-198.

参考文献

[1] 田晶, 艾廷华, 丁绍军. 基于C4.5算法的道路网网格模式识别[J]. 测绘学报, 2012, 41(1): 121-126. TIAN Jing, AI Tinghua, DING Shaojun. Grid pattern recognition in road networks based on C4.5 algorithm[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(1): 121-126.
[2] HE Hao, WANG Shuyang, WANG Shicheng, et al. A road extraction method for remote sensing image based on encoder-decoder network[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(2): 16-25.
[3] PEI Hongxing, ZHAI Renjian, WU Fang, et al. Automatic matching of multi-scale road networks under the constraints of smaller scale road meshes[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(4): 73-83.
[4] HEINZLE F, ANDERS K H, SESTER M. Pattern recognition in road networks on the example of circular road detection[C]//Procee-dings of the 4th International Conference on Geographic Information Science. Berlin: Springer, 2006: 153-167.
[5] ZHANG Qingnian. Modeling structure and patterns in road network generalization[EB/OL].[2023-02-02]. http://static.aminer.org/pdf/PDF/000/236/515/exploiting_perceptual_grouping_for_map_analysis_understanding_and_generalization_the.pdf.
[6] HEINZLE F, ANDERS K H, SESTER M. Graph based approaches for recognition of patterns and implicit information in road networks[EB/OL]. [2023-02-02]. https://www.researchgate.net/publication/228646856_Graph_based_approaches_for_recognition_of_patterns_and_implicit_information_in_road_networks.
[7] 田晶, 宋子寒, 艾廷华. 运用图论进行道路网网格模式提取[J]. 武汉大学学报(信息科学版), 2012, 37(6): 724-727. TIAN Jing, SONG Zihan, AI Tinghua. Grid pattern extraction in road networks with graph[J]. Geomatics and Information Science of Wuhan University, 2012, 37(6): 724-727.
[8] HE Yakun, AI Tinghua, YU Wenhao, et al. A linear tessellation model to identify spatial pattern in urban street networks[J]. International Journal of Geographical Information Science, 2017, 31(8): 1541-1561.
[9] 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. WANG Miqi, AI Tinghua, YAN Xiongfeng, et al. Grid pattern recognition in road networks based on graph convolution network model[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1960-1969.
[10] LOUF R, BARTHELEMY M. A typology of street patterns[J]. Journal of the Royal Society, Interface, 2014, 11(101): 924-933.
[11] HEINZLE F, ANDERS K H. Characterising space via pattern recognition techniques[M]//MACKANESS W A, RUAS A, SARJAKOSKI L T. Generalisation of geographic information: cartographic modelling and application.New York: Elsevier, 2007: 233-253.
[12] HEINZLE F, ANDERS K H, SESTER M. Automatic detection of pattern in road networks-methods and evaluation[EB/OL].[2023-02-02].https://www.isprs.org/proceedings/XXXVI/4-W45/PDF/21_Heinzle.pdf.
[13] YANG Bisheng, LUAN Xuechen, LI Qingquan. An adaptive method for identifying the spatial patterns in road networks[J]. Computers, Environment and Urban Systems, 2010, 34(1): 40-48.
[14] TIAN Jing, SONG Zihan, GAO Fei, et al. Grid pattern recognition in road networks using the C4.5 algorithm[J]. Cartography and Geographic Information Science, 2016, 43(3): 266-282.
[15] AI Tinghua, CHENG Xiaoqiang, LIU Pengcheng, et al. A shape analysis and template matching of building features by the Fourier transform method[J]. Computers, Environment and Urban Systems, 2013, 41: 219-233.
[16] STEINIGER S. Enabling pattern aware automated map generalization [D]. Zurich: University of Zurich, 2007.
[17] WANG Xuesong, YOU Shikai, WANG Ling. Classifying road network patterns using multinomial logit model[J]. Journal of Transport Geography, 2017, 58: 104-112.
[18] ROSIN P L. Measuring rectangularity[J]. Machine Vision and Applications, 1999, 11(4): 191-196.
[19] 杨必胜, 张云菲, 栾学晨. 保持几何模式的城市道路格网简化方法[J]. 中国图象图形学报, 2012, 17(1): 150-156. YANG Bisheng, ZHANG Yunfei, LUAN Xuechen. Pattern preserving method for grid simplification in road networks[J]. Journal of Image and Graphics, 2012, 17(1): 150-156.
[20] DOUGLAS D H, PEUCKER T K. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature[J]. Cartographica: the International Journal for Geographic Information and Geovisualization, 1973, 10(2): 112-122.
[21] KIM C E, ANDERSON T A. Digital disks and a digital compactness measure[C]//Proceedings of the 16th annual ACM Symposium on Theory of Computing. NewYork: ACM Press, 1984: 117-124.
[22] 刘耀林, 刘启亮, 邓敏, 等. 地理大数据挖掘研究进展与挑战[J]. 测绘学报, 2022, 51(7): 1544-1560. DOI: 10.11947/j.AGCS.2022.20220068. LIU Yaolin, LIU Qiliang, DENG Min, et al. Recent advance and challenge in geospatial big data mining[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1544-1560. DOI: 10.11947/j.AGCS.2022.20220068.
[23] KINGMA D P, WELLING M. Auto-encoding variational Bayes[EB/OL].[2023-02-02]. http://arxiv.org/abs/1312.6114.pdf.
[24] SPECHT D F. Probabilistic neural networks[J]. Neural Networks, 1990, 3(1): 109-118.
[25] AHMADLOU M, ADELI H. Enhanced probabilistic neural network with local decision circles: a robust classifier[J]. Integrated Computer-Aided Engineering, 2010, 17(3): 197-210.
[26] 吴顺川, 张晨曦, 成子桥. 基于PCA-PNN原理的岩爆烈度分级预测方法[J]. 煤炭学报, 2019, 44(9): 2767-2776. WU Shunchuan, ZHANG Chenxi, CHENG Ziqiao. Prediction of intensity classification of rockburst based on PCA-PNN principle[J]. Journal of China Coal Society, 2019, 44(9): 2767-2776.
[27] SUN Qian, WU Chong, LI Yongli. A new probabilistic neural network model based on backpropagation algorithm[J]. Journal of Intelligent & Fuzzy Systems, 2017, 32(1): 215-227.
[28] BERTHOLD M R, DIAMOND J. Constructive training of probabilistic neural networks[J]. Neurocomputing, 1998, 19(1/2/3): 167-183.
[29] DIETTERICH T G. Approximate statistical tests for comparing supervised classification learning algorithms[J]. Neural Computation, 1998, 10(7): 1895-1923.
[30] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.
[31] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323: 533-536.

利用多层次网眼特征和VAE-PNN模型识别城市道路格网模式

Grid patterns recognition in urban road networks using multi-level mesh features and VAE-PNN model

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价