EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vision-Based Trajectory Reconstruction in Human Activities: Methodology and Application

Jasper Lottefier iD, Peter Van den Broeck iD, Katrien Van Nimmen iD

Sensors · 13.12.2025 · 25 (24) · 7577

DOI: 10.3390/s25247577 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.12.2025. Verfasst von Jasper Lottefier und 2 weiteren Autor:innen. Beteiligte Einrichtung: Structural Mechanics, Department of Civil Engineering, KU Leuven, B-9000 Ghent, Belgium. Hauptthemen laut MEDLINE: Human Activities, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Foundation - Flanders, Research Foundation Flanders.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern civil engineering structures, such as footbridges, are increasingly susceptible to vibrations induced by human activities, emphasizing the importance of accurately assessing crowd-induced loading. Developing realistic load models requires detailed insight into the underlying crowd dynamics, which in turn depend on the coordination between individuals and the spatial organization of the group. A deeper understanding of these human–human interactions is therefore essential for capturing the collective behaviour that governs crowd-induced vibrations. This paper presents a vision-based trajectory reconstruction methodology that captures individual movement trajectories in both small groups and large-scale running events. The approach integrates colour-based image segmentation for instrumented participants, deep learning–based object detection for uninstrumented crowds, and a homography-based projection method to map image coordinates to world space. The methodology is applied to empirical data from two urban running events and controlled experiments, including both stationary and dynamic camera perspectives. Results show that the framework reliably reconstructs individual trajectories under varied field conditions, applicable to both walking and running activities. The approach enables scalable monitoring of human activities and provides high-resolution spatio-temporal data for studying human–human interactions and modelling crowd dynamics. In this way, the findings highlight the potential of vision-based methods as practical, non-intrusive tools for analysing human-induced loading in both research and applied engineering contexts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Human ActivitiesImage Processing, Computer-AssistedHumansRunningWalkingDeep Learning

Stichwörter der Autor:innen

crowd dynamics measurement frameworksdrone-based object trackingempirical trajectory reconstructionintegrated human movement measurements

Autor:innen und Institutionen

  • Structural Mechanics, Department of Civil Engineering, KU Leuven, B-9000 Ghent, Belgium.

ORCID-Profile: Jasper Lottefier, Peter Van den Broeck, Katrien Van Nimmen

Förderung

  • Research Foundation - Flanders
  • Research Foundation Flanders

Zitieren

APA

Lottefier, J., Van den Broeck, P., & Van Nimmen, K. (2025). Vision-Based Trajectory Reconstruction in Human Activities: Methodology and Application. Sensors, 25(24), 7577. https://doi.org/10.3390/s25247577

Vancouver

Lottefier J, Van den Broeck P, Van Nimmen K. Vision-Based Trajectory Reconstruction in Human Activities: Methodology and Application. Sensors. 2025;25(24):7577. doi:10.3390/s25247577

BibTeX
@article{Lottefier2025,
  author = {Lottefier, Jasper and Van den Broeck, Peter and Van Nimmen, Katrien},
  title = {Vision-Based Trajectory Reconstruction in Human Activities: Methodology and Application},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {24},
  pages = {7577},
  doi = {10.3390/s25247577}
}
Kostenlos starten →