Pedestrian Movement Prediction and Pattern Analysis

Understanding pedestrian movement patterns is essential for designing accessible and pedestrian-friendly urban environments. By analysing them, city planners can optimize resource allocation, enhance walkability, and improve infrastructure planning. This study examines pedestrian patterns in Distric...

Full description

Saved in:
Bibliographic Details
Main Authors: V. Toshev, K. Karamitov, D. Petrova-Antonova
Format: Article
Language:English
Published: Copernicus Publications 2025-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1447/2025/isprs-archives-XLVIII-G-2025-1447-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850069337770033152
author V. Toshev
K. Karamitov
D. Petrova-Antonova
D. Petrova-Antonova
author_facet V. Toshev
K. Karamitov
D. Petrova-Antonova
D. Petrova-Antonova
author_sort V. Toshev
collection DOAJ
description Understanding pedestrian movement patterns is essential for designing accessible and pedestrian-friendly urban environments. By analysing them, city planners can optimize resource allocation, enhance walkability, and improve infrastructure planning. This study examines pedestrian patterns in District Lozenets of Sofia city, Bulgaria, and develops a predictive model to estimate foot traffic based on environmental factors such as weather conditions and pedestrian density at different times of day.<br />The study utilizes data for pedestrian movement collected in the GATE Institute&rsquo;s City Living Lab in District Lozenets, employing radar-based sensors and incorporating weather data to analyse pedestrian movement trends. Furthermore, it explores various statistical models, such as ARIMA and ETS models, to forecast pedestrian traffic. Results indicate strong seasonal trends, with weekday peaks during commuting hours and a decline in foot traffic due to adverse weather conditions such as rain and snow. The SARIMA model demonstrates high accuracy in predicting short-term pedestrian movement patterns, outperforming alternative models in capturing both seasonal variations and long-term trends.<br />The findings provide valuable insights for urban planners, event organizers, and policymakers, enabling data-driven decisions for infrastructure improvements, public safety strategies, and pedestrian-friendly city planning. The study also highlights the potential of digital twin technology in urban mobility research, demonstrating the benefits of integrating real-time pedestrian data for predictive analytics.
format Article
id doaj-art-ba6cc88bc403417384b79bd5192945cb
institution DOAJ
issn 1682-1750
2194-9034
language English
publishDate 2025-08-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-ba6cc88bc403417384b79bd5192945cb2025-08-20T02:47:47ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-08-01XLVIII-G-20251447145410.5194/isprs-archives-XLVIII-G-2025-1447-2025Pedestrian Movement Prediction and Pattern AnalysisV. Toshev0K. Karamitov1D. Petrova-Antonova2D. Petrova-Antonova3Faculty of Mathematics and Informatics, Sofia University, Sofia, BulgariaGATE Institute, Sofia University, Sofia, BulgariaFaculty of Mathematics and Informatics, Sofia University, Sofia, BulgariaGATE Institute, Sofia University, Sofia, BulgariaUnderstanding pedestrian movement patterns is essential for designing accessible and pedestrian-friendly urban environments. By analysing them, city planners can optimize resource allocation, enhance walkability, and improve infrastructure planning. This study examines pedestrian patterns in District Lozenets of Sofia city, Bulgaria, and develops a predictive model to estimate foot traffic based on environmental factors such as weather conditions and pedestrian density at different times of day.<br />The study utilizes data for pedestrian movement collected in the GATE Institute&rsquo;s City Living Lab in District Lozenets, employing radar-based sensors and incorporating weather data to analyse pedestrian movement trends. Furthermore, it explores various statistical models, such as ARIMA and ETS models, to forecast pedestrian traffic. Results indicate strong seasonal trends, with weekday peaks during commuting hours and a decline in foot traffic due to adverse weather conditions such as rain and snow. The SARIMA model demonstrates high accuracy in predicting short-term pedestrian movement patterns, outperforming alternative models in capturing both seasonal variations and long-term trends.<br />The findings provide valuable insights for urban planners, event organizers, and policymakers, enabling data-driven decisions for infrastructure improvements, public safety strategies, and pedestrian-friendly city planning. The study also highlights the potential of digital twin technology in urban mobility research, demonstrating the benefits of integrating real-time pedestrian data for predictive analytics.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1447/2025/isprs-archives-XLVIII-G-2025-1447-2025.pdf
spellingShingle V. Toshev
K. Karamitov
D. Petrova-Antonova
D. Petrova-Antonova
Pedestrian Movement Prediction and Pattern Analysis
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Pedestrian Movement Prediction and Pattern Analysis
title_full Pedestrian Movement Prediction and Pattern Analysis
title_fullStr Pedestrian Movement Prediction and Pattern Analysis
title_full_unstemmed Pedestrian Movement Prediction and Pattern Analysis
title_short Pedestrian Movement Prediction and Pattern Analysis
title_sort pedestrian movement prediction and pattern analysis
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1447/2025/isprs-archives-XLVIII-G-2025-1447-2025.pdf
work_keys_str_mv AT vtoshev pedestrianmovementpredictionandpatternanalysis
AT kkaramitov pedestrianmovementpredictionandpatternanalysis
AT dpetrovaantonova pedestrianmovementpredictionandpatternanalysis
AT dpetrovaantonova pedestrianmovementpredictionandpatternanalysis