Automatic physical fatigue assessment for construction workers based on computer vision and pressure insole sensor

Abstract

The construction industry around the globe has unsatisfactory occupational health and safety records. One of the major reasons is attributed to high physical demands and hostile working environments. Construction work always requires workers to work for a long duration without sufficient breaks to recover from overexertion, and to work under harsh climatic conditions and/or in confined workspaces. Such circumstances can increase the risk of fatigue, which may lead to work-related musculoskeletal disorders (MSDs) and accidents on construction sites. With a growing proportion of older workers in many countries/regions, it is paramount to improve the occupational health and safety of construction workers in order to sustain the current construction workforce. Since fatigue poses a major challenge to occupational health and safety, fatigue monitoring and management has become an issue of utmost prominence. Traditionally, physical fatigue monitoring in the construction domain relies on self-reporting or subjective questionnaires. These methods require the manual collection of responses and are impractical for continuous fatigue monitoring. Some researchers have used on-body sensors for fatigue monitoring (such as heart rate monitors and surface electromyography (sEMG) sensors). Although these devices appear to be promising, they are intrusive, requiring sensors to be attached to the worker's body. Such on-body sensors are uncomfortable to wear and could easily cause irritation. Considering the limitations of these methodologies, the authors propose a novel non-intrusive method to monitor whole-body fatigue by combining computer vision technology and smart insoles for construction workers. Specifically, a computer vision-based 3D motion capture algorithm was developed to model the motion of various body parts using an RGB camera. Further, smart insoles capable of monitoring the reaction forces of feet generated by a work-pattern was applied with a self-charging capacity. A fatigue assessment indicator was developed using the force data from the insoles, the 3D model data from the developed motion capture algorithm and inverse dynamics modeling. A series of laboratory experiments demonstrate the accuracy and feasibility of the data collection methods and physical fatigue assessment (PFA) method. Field experiments demonstrate that the proposed method can not only be easily used by the construction industry to monitor the risk of overexertion and fatigue among workers but also contribute to improving construction site layout and schedule management aiming at improving construction workers safety.