Recognizing Actions in High-Resolution Low-Framerate Videos: A Feasibility Study in the Construction Sector

Benjamin Vandersmissen, Arian Sabaghi, Phil Reiter, Jose Oramas

2024

Abstract

Action recognition addresses the automated comprehension of human actions within images or video sequences. Its applications extend across critical areas, mediating between visual perception and intelligent decision-making. However, action recognition encounters multifaceted challenges, including limited annotated data, background clutter, and varying illumination conditions. In the context of the construction sector, distinct challenges arise, requiring specialized approaches. This study investigates the applicability of established action recognition methodologies in this dynamic setting. We evaluate both sequence-based (YOWO) and frame-based (YOLOv8) approaches, considering the effect that resolution and frame rate have on performance. Additionally, we explore self-supervised learning techniques to enhance recognition accuracy. Our analysis aims to guide the development of more effective and efficient practical action recognition methods.

Paper Citation

in Harvard Style

Vandersmissen B., Sabaghi A., Reiter P. and Oramas J. (2024). Recognizing Actions in High-Resolution Low-Framerate Videos: A Feasibility Study in the Construction Sector. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 593-600. DOI: 10.5220/0012423900003660

in Bibtex Style

@conference{visapp24,
author={Benjamin Vandersmissen and Arian Sabaghi and Phil Reiter and Jose Oramas},
title={Recognizing Actions in High-Resolution Low-Framerate Videos: A Feasibility Study in the Construction Sector},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP},
year={2024},
pages={593-600},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012423900003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP
TI - Recognizing Actions in High-Resolution Low-Framerate Videos: A Feasibility Study in the Construction Sector
SN - 978-989-758-679-8
AU - Vandersmissen B.
AU - Sabaghi A.
AU - Reiter P.
AU - Oramas J.
PY - 2024
SP - 593
EP - 600
DO - 10.5220/0012423900003660
PB - SciTePress