EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Stream Fusion Network for Skeleton-Based Construction Worker Action Recognition

Yuanyuan Tian, Yan Liang, Haibin Yang iD, Jiayu Chen

Sensors · 2023

DOI: 10.3390/s23239350 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Yuanyuan Tian und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Architecture and Civil Engineering, City University of Hong Kong, Hong Kong 999077, China. Hauptthemen laut MEDLINE: Construction Industry, Musculoskeletal System. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The global concern regarding the monitoring of construction workers’ activities necessitates an efficient means of continuous monitoring for timely action recognition at construction sites. This paper introduces a novel approach—the multi-scale graph strategy—to enhance feature extraction in complex networks. At the core of this strategy lies the multi-feature fusion network (MF-Net), which employs multiple scale graphs in distinct network streams to capture both local and global features of crucial joints. This approach extends beyond local relationships to encompass broader connections, including those between the head and foot, as well as interactions like those involving the head and neck. By integrating diverse scale graphs into distinct network streams, we effectively incorporate physically unrelated information, aiding in the extraction of vital local joint contour features. Furthermore, we introduce velocity and acceleration as temporal features, fusing them with spatial features to enhance informational efficacy and the model’s performance. Finally, efficiency-enhancing measures, such as a bottleneck structure and a branch-wise attention block, are implemented to optimize computational resources while enhancing feature discriminability. The significance of this paper lies in improving the management model of the construction industry, ultimately aiming to enhance the health and work efficiency of workers.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Construction IndustryMusculoskeletal SystemHumansSkeletonFootLower Extremity

Stichwörter der Autor:innen

3D skeleton dataconstruction worker action recognitiondeep learning algorithmmulti-stream network

Autor:innen und Institutionen

  • Department of Architecture and Civil Engineering, City University of Hong Kong, Hong Kong 999077, China.
  • Key Laboratory for Resilient Infrastructures of Coastal Cities (MOE), College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, China.
  • School of Civil Engineering, Tsinghua University, Beijing 100084, China.

ORCID-Profile: Haibin Yang

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of China

Zitieren

APA

Tian, Y., Liang, Y., Yang, H., & Chen, J. (2023). Multi-Stream Fusion Network for Skeleton-Based Construction Worker Action Recognition. Sensors. https://doi.org/10.3390/s23239350

Vancouver

Tian Y, Liang Y, Yang H, Chen J. Multi-Stream Fusion Network for Skeleton-Based Construction Worker Action Recognition. Sensors. 2023. doi:10.3390/s23239350

BibTeX
@article{Tian2023,
  author = {Tian, Yuanyuan and Liang, Yan and Yang, Haibin and Chen, Jiayu},
  title = {Multi-Stream Fusion Network for Skeleton-Based Construction Worker Action Recognition},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23239350}
}
Kostenlos starten →