EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Camera-Based Human Activity Recognition for Human–Robot Collaboration in Construction

Youjin Jang iD, Inbae Jeong, Moein Younesi Heravi, Sajib Sarkar, Hyunkyu Shin, Yonghan Ahn

Sensors · 07.08.2023 · 23 (15) · 6997

DOI: 10.3390/s23156997 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.08.2023. Verfasst von Youjin Jang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil, Construction and Environmental Engineering, North Dakota State University, Fargo, ND 58108, USA. Hauptthemen laut MEDLINE: Robotics. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Energy Technology Evaluation and Planning.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the use of construction robots continues to increase, ensuring safety and productivity while working alongside human workers becomes crucial. To prevent collisions, robots must recognize human behavior in close proximity. However, single, or RGB-depth cameras have limitations, such as detection failure, sensor malfunction, occlusions, unconstrained lighting, and motion blur. Therefore, this study proposes a multiple-camera approach for human activity recognition during human–robot collaborative activities in construction. The proposed approach employs a particle filter, to estimate the 3D human pose by fusing 2D joint locations extracted from multiple cameras and applies long short-term memory network (LSTM) to recognize ten activities associated with human and robot collaboration tasks in construction. The study compared the performance of human activity recognition models using one, two, three, and four cameras. Results showed that using multiple cameras enhances recognition performance, providing a more accurate and reliable means of identifying and differentiating between various activities. The results of this study are expected to contribute to the advancement of human activity recognition and utilization in human–robot collaboration in construction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsHumansMotionLighting

Stichwörter der Autor:innen

human activity recognitionhuman pose estimationlong short-term memorymultiple camerasparticle filter

Autor:innen und Institutionen

  • Department of Civil, Construction and Environmental Engineering, North Dakota State University, Fargo, ND 58108, USA.
  • Department of Mechanical Engineering, North Dakota State University, Fargo, ND 58108, USA.
  • Sustainable Smart City Convergence Educational Research Center, Hanyang University ERICA, Ansan 15588, Republic of Korea.
  • Department of Architectural Engineering, Hanyang University ERICA, Ansan 15588, Republic of Korea.

ORCID-Profile: Youjin Jang

Förderung

  • Korea Institute of Energy Technology Evaluation and Planning

Zitieren

APA

Jang, Y., Jeong, I., Younesi Heravi, M., Sarkar, S., Shin, H., & Ahn, Y. (2023). Multi-Camera-Based Human Activity Recognition for Human–Robot Collaboration in Construction. Sensors, 23(15), 6997. https://doi.org/10.3390/s23156997

Vancouver

Jang Y, Jeong I, Younesi Heravi M, Sarkar S, Shin H, Ahn Y. Multi-Camera-Based Human Activity Recognition for Human–Robot Collaboration in Construction. Sensors. 2023;23(15):6997. doi:10.3390/s23156997

BibTeX
@article{Jang2023,
  author = {Jang, Youjin and Jeong, Inbae and Younesi Heravi, Moein and Sarkar, Sajib and Shin, Hyunkyu and Ahn, Yonghan},
  title = {Multi-Camera-Based Human Activity Recognition for Human–Robot Collaboration in Construction},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {15},
  pages = {6997},
  doi = {10.3390/s23156997}
}
Kostenlos starten →