Calibration of pedestrian ingress model based on CCTV surveillance data using machine learning methods

Simple item page
dc.contributor.authorPálková, Martinacs
dc.contributor.authorUhlík, Ondřejcs
dc.contributor.authorApeltauer, Tomášcs
dc.coverage.issue1cs
dc.coverage.volume19cs
dc.date.accessioned2024-05-10T13:45:36Z
dc.date.available2024-05-10T13:45:36Z
dc.date.issued2024-01-18cs
dc.description.abstractMachine learning methods and agent-based models enable the optimization of the operation of high capacity facilities. In this paper, we propose a method for automatically extracting and cleaning pedestrian traffic detector data for subsequent calibration of the ingress pedestrian model. The data was obtained from the waiting room traffic of a vaccination center. Walking speed distribution, the number of stops, the distribution of waiting times, and the locations of waiting points were extracted. Of the 9 machine learning algorithms, the random forest model achieved the highest accuracy in classifying valid data and noise. The proposed microscopic calibration allows for more accurate capacity assessment testing, procedural changes testing, and geometric modifications testing in parts of the facility adjacent to the calibrated parts. The results show that the proposed method achieves state-of-the-art performance on a violent-flows dataset. The proposed method has the potential to significantly improve the accuracy and efficiency of input model predictions and optimize the operation of high-capacity facilities.en
dc.formattextcs
dc.format.extent22cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationPLOS ONE. 2024, vol. 19, issue 1, 22 p.en
dc.identifier.doi10.1371/journal.pone.0293679cs
dc.identifier.issn1932-6203cs
dc.identifier.orcid0000-0002-8001-6349cs
dc.identifier.orcid0000-0001-9047-4784cs
dc.identifier.orcid0000-0003-3186-2175cs
dc.identifier.other187059cs
dc.identifier.researcheridQ-2414-2015cs
dc.identifier.scopus35067734400cs
dc.identifier.urihttps://hdl.handle.net/11012/245484
dc.language.isoencs
dc.publisherPublic Library of Sciencecs
dc.relation.ispartofPLOS ONEcs
dc.relation.urihttps://journals.plos.org/plosone/article?id=10.1371/journal.pone.0293679cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1932-6203/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectpedestrian modellingen
dc.subjectagent-based modelsen
dc.subjectmachine learningen
dc.subjectrandom foresten
dc.subjectcalibrationen
dc.subjectsurveillanceen
dc.titleCalibration of pedestrian ingress model based on CCTV surveillance data using machine learning methodsen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-187059en
sync.item.dbtypeVAVen
sync.item.insts2024.05.10 15:45:36en
sync.item.modts2024.05.10 15:13:10en
thesis.grantorVysoké učení technické v Brně. Fakulta stavební. Ústav automatizace inženýrských úloh a informatikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
journal.pone.0293679.pdf
Size:
3.54 MB
Format:
Adobe Portable Document Format
Description:
file journal.pone.0293679.pdf
Download
Collections
Ústav automatizace inženýrských úloh a informatiky