Damien Burlet-Vienney

Computer vision (CV) technologies have emerged as promising tools for real-time collision risk management. This paper examines CV-based collision-prevention systems from academic and industrial perspectives with a focus on identifying technical and implementation challenges affecting their deployment on construction sites. A scoping review of 158 publications was conducted, alongside an assessment of commercial CV-based collision-prevention systems currently used in construction. The analysis focused on five key functions: object detection, distance measurement and proximity estimation, tracking, worker re-identification (ReID), and deployment robustness. Academic studies demonstrate substantial progress in detection accuracy, real-time processing, trajectory tracking, and predictive risk assessment through deep learning approaches. However, performance remains sensitive to occlusions, lighting variations, environmental conditions, and site-specific characteristics. The commercial systems assessed in this study, while generally designed for reliability and ease of integration, often rely on simplified zone-based warning logic and provide limited transparency regarding performance validation, tracking capabilities, and distance estimation accuracy. The review highlights a persistent gap between laboratory performance and operational effectiveness on construction sites. The findings point to the need for greater robustness under real-world conditions, validated metric-distance accuracy, improved temporal continuity through tracking and ReID, and standardized evaluation protocols incorporating safety-relevant performance metrics. As AI-enabled systems increasingly support safety-related functions, their development should also align with established machine-safety principles and emerging standards.

Canada’s agricultural sector included 189,874 farms in 2021, 15% of which were located in the province of Quebec. Farmers are exposed to a variety of

Vehicles falling off two-post above-ground (2PAG) lifts is a fairly frequent occurrence. As only limited knowledge is available about the determinants influencing the stability of lifting vehicles with a 2PAG lift, two experimental designs were carried out in order to have quantitative data. This paper addresses support pad slippage as a result of external forces being exerted on a vehicle. The experimental design is based on the consultation of the key players that identify the main issues related to the support pads. The controlled factors chosen in this experimental design were lift support pad type and position, smear on pads, arm locking and external force type. Based on the analysis of variance, factors that had a significant influence on the support pad slippage were (i) support pad type, (ii) external force type and (iii) the interaction between those two controlled factors. Arm locking and support pad position were not statistically significant. From a practical standpoint, initial placement of the support pad is, however, a major safety measure, as support pad slippage went up to 53% of the pad half-width. These results should challenge 2PAG lift manufacturers and vehicle manufacturers to come up with support pad and lifting point designs, respectively, that would reduce this inherent risk of the 2PAG lifts.

Industrial machines are known to possess many hazards. There are many laws, regulations, standards and practices that aim at ensuring that machines are safe for different workers performing various tasks including operation and maintenance. Safeguards protect workers by stopping hazardous motion when actuated. Those safeguards are integrated into machinery using two widely used international standards for functional safety. However, these standards have some significant differences although they are both based on similar principles. This paper explores those differences and their potential impacts. Subjectivity in the specification and design of safety systems, based on the differences, can lead to different levels of reliability in the safety systems even when considering the same hazard zone of machinery based on which standard is used.

Failure to apply lockout procedures for the control of hazardous energies is one of the main causes of machinery-related fatal and serious injuries in North America. The absence of audits of lockout or the lack of proper tools for auditing lockout is prevalent, and thus the application of lockout is often not fully in compliance with standards and regulations. A self-audit tool for the application of lockout procedures for machinery was developed on the basis of the current standards and regulations, and previous research. The tool was then tested for content validity through experts’ opinions and qualitative feedback from six organizations in the province of Quebec in Canada. The developed audit tool defines the actual procedures to audit, as well as the surrounding conditions that are needed and the prerequisites based on standards, regulations, and findings from previous research. The results showed that the tool displayed a high content validity index and demonstrated that the usability, applicability, and comprehensiveness of the tool were adequate. This self-audit tool helps organizations monitor the application of lockout on machinery for the safety of workers and to ensure that the actual practice of controlling hazardous energy is in compliance with relevant standards and regulations.