Work-related musculoskeletal disorders (WMSDs) represent a significant health challenge for workers in construction environments, often arising from prolonged exposure to ergonomic risks associated with manual labor, awkward postures, and repetitive motions. These conditions not only lead to diminished worker productivity but also incur substantial economic costs for employers and healthcare systems alike. Thus, there is an urgent need for effective tools to assess and mitigate these ergonomic risks. This study proposes a novel monocular 3D multi-person pose estimation method designed to enhance ergonomic risk assessments in construction environments. Leveraging advanced computer vision and deep learning techniques, this approach accurately captures and analyzes the spatial dynamics of workers’ postures, with a focus on detecting extreme knee flexion, a critical indicator of work-related musculoskeletal disorders (WMSDs). A pilot study conducted on an actual construction site demonstrated the method’s feasibility and effectiveness, achieving an accurate detection rate for extreme flexion incidents that closely aligned with supervisory observations and worker self-reports. The proposed monocular approach enables universal applicability and enhances ergonomic analysis through 3D pose estimation and group pose recognition for timely interventions. Future efforts will focus on improving robustness and integration with health monitoring to reduce WMSDs and promote worker health.
22 June 2026 in Engineering, Construction and Architectural Management
Purpose: This paper aims to develop a proactive construction safety management framework capable of predicting near-miss incidents by leveraging Digital Twin (DT) technology. The Digital Twin (DT) framework focuses on integrating environmental and human-related risk factors – particularly the trajectories and behaviors of workers – before accidents occur. Design/methodology/approach: The paper proposes a computer vision-based digital twin framework that integrates real-time data on workers' movements, postures, and interactions to construct a dynamic 3D model of the construction site. Deep learning algorithms are employed to predict human trajectories and behaviors, while collision detection techniques are used to identify potential near-miss scenarios. Field validation was conducted in three high-risk zones: forklift paths, floor openings, and material lifting areas. Findings: The proposed framework achieved high accuracy in predicting near-miss events and provided timely early warnings, outperforming traditional 2D monitoring methods. The system's capability to visualize worker interactions and spatial hazards in 3D significantly enhanced situational awareness and safety decision-making on site. Practical implications: By transitioning from 2D to 3D monitoring and from post-event detection to real-time prediction, the proposed system enables early identification of near-miss risks during ongoing construction activities. Its integration of 3D visualization and digital twin technology provides intuitive, actionable insights, empowering safety managers to intervene proactively and enhance on-site safety performance. Originality/value: This paper introduces an innovative approach that transitions safety management from passive detection to proactive prediction. By integrating digital twin technology with deep learning, it enables 3D visualization and prediction of near-miss incidents and supports real-time, data-driven safety interventions. The proposed system contributes to the advancement of intelligent, predictive safety management solutions in the construction industry, with a particular focus on forecasting near-miss events before they escalate into actual accidents.