Justin Worsey, I. Hindmarch, S. Armour, David R. Bull
{"title":"Observations from using a portable LIDAR scanner to capture RF propagation modelling environments","authors":"Justin Worsey, I. Hindmarch, S. Armour, David R. Bull","doi":"10.1109/5GWF52925.2021.00053","DOIUrl":null,"url":null,"abstract":"Automated assessment of a 3D geographical environment is highly desirable for many reasons including the creation of accurate environments for RF propagation modelling tools to assist in network planning, and for the rapid deployment of communication aids in areas affected by war or natural disasters. This paper presents some of the observations and limitations of using a portable Laser Imaging, Detection and Ranging (LIDAR) scanner to capture the data points. The point cloud was subsequently classified using a deep learning network before being translated into mesh based environments. Observations include issues with the capturing technique, where a single person can be captured multiple times; a lack of scanner range which permitted false free space line-of-site (LOS) propagation and unexpected classification issues which impacted radio wave propagation. By addressing these observations, cheap and portable LIDAR scanners can provide a viable technique to assist network planning.","PeriodicalId":226257,"journal":{"name":"2021 IEEE 4th 5G World Forum (5GWF)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 4th 5G World Forum (5GWF)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/5GWF52925.2021.00053","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Automated assessment of a 3D geographical environment is highly desirable for many reasons including the creation of accurate environments for RF propagation modelling tools to assist in network planning, and for the rapid deployment of communication aids in areas affected by war or natural disasters. This paper presents some of the observations and limitations of using a portable Laser Imaging, Detection and Ranging (LIDAR) scanner to capture the data points. The point cloud was subsequently classified using a deep learning network before being translated into mesh based environments. Observations include issues with the capturing technique, where a single person can be captured multiple times; a lack of scanner range which permitted false free space line-of-site (LOS) propagation and unexpected classification issues which impacted radio wave propagation. By addressing these observations, cheap and portable LIDAR scanners can provide a viable technique to assist network planning.