Automated recognition of regular, radial and ring structures in the configuration of a street-road network of settlements

Author:

Shurygina Anastasia1,Samsonov Timofey1

Affiliation:

1. Moscow State University named after M.V. Lomonosov, Leninskie Gory, 1, 119991, Moscow, Russia

Abstract

The article describes the experience of applying various approaches to the recognition of some of the most common settlements planning structures, which include radial, regular and ring elements. At the first stage, it is necessary to identify typical properties and elements of the corresponding figures, then find a way to automate the search for such entities in an arbitrary road network of a settlement. To solve the second problem, well-known algorithms are used that are associated with the analysis of the uniformity of the shape of neighborhoods of a settlement. Modifications of the algorithm for searching for radial structural elements are proposed, and the author’s method of detecting ring elements is tested. The selected approaches are implemented in the form of a script in the Python programming language, which sequentially checks the road network given to the input for the presence of lattice or radial-ring planning structure elements. The technique was tested in fifty cities of the world. Verification of the results was carried out by comparing the response of the algorithm with the expert opinion of the research authors or literature on the topic. The accuracy of the classification was 80 %. The algorithm successfully coped with the reference examples of layouts, but experienced difficulties with their modifications, associated, for example, with the lack of closure of the ring elements of the radial-ring structure. The results can be demanded in problems of cartographic generalization, which require recognition and preservation of typical features of spatial objects.

Publisher

LLC Kartfond

Subject

General Engineering

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3