EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparison of methods to determine pedestrian shoulder orientation from stereo recordings

Deniz Kılıç, Maik Boltes

Acta Polytechnica CTU Proceedings · 16.06.2026 · 57 · 159-167

DOI: 10.14311/app.2026.57.0159 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Polytechnica CTU Proceedings, online erschienen am 16.06.2026. Verfasst von Deniz Kılıç und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The orientation of pedestrians is used for analysis of space usage, social groups or orientation dynamics in crowds. For this purpose, it is desirable to measure the orientation for each pedestrian in the crowd. This work compares geometric and machine learning methods to determine the shoulder orientation. We make use of stereo camera systems to enable the estimation without the need for intrusive measurement equipment.The machine learning methods consistently outperform the geometric methods. Especially in higher densities. However, high-density and low movement datasets are still challenging for machine learning techniques with automated labels. In laboratory experiments, coloured shoulder markers can be a cost-effective alternative method.

Zitieren

APA

Kılıç, D., & Boltes, M. (2026). Comparison of methods to determine pedestrian shoulder orientation from stereo recordings. Acta Polytechnica CTU Proceedings, 57, 159-167. https://doi.org/10.14311/app.2026.57.0159

Vancouver

Kılıç D, Boltes M. Comparison of methods to determine pedestrian shoulder orientation from stereo recordings. Acta Polytechnica CTU Proceedings. 2026;57:159-167. doi:10.14311/app.2026.57.0159

BibTeX
@article{Kl2026,
  author = {Kılıç, Deniz and Boltes, Maik},
  title = {Comparison of methods to determine pedestrian shoulder orientation from stereo recordings},
  journal = {Acta Polytechnica CTU Proceedings},
  year = {2026},
  volume = {57},
  pages = {159--167},
  doi = {10.14311/app.2026.57.0159}
}
Kostenlos starten →