Automated 3D Ergonomic Assessment from a Single Standard Camera for Confirmation of Work Overload of Lumbar Spine

Abstract: Chronic lumbar spine disease is a new item on the list of occupational diseases in the Czech Republic from January 1, 2023. This disease is defined by clear clinical characteristics and necessary exposure criteria at work. The diseases arise during heavy physical work, during which the relevant structures are overloaded for a long time to such an extent that, according to current medical knowledge, overloading is the cause of the disease.The essential exposure criterion is the determination and confirmation of work tasks, work activities and work shifts in which the hygienic limits set by Government Decree No. 361/2007 Coll., as amended, for handling loads, taking into account the working position, are exceeded. To meet the hygienic exposure criteria, it must be confirmed that the compression force on the L4/L5 disc exceeds the value based on the NIOSH US 3400 N limit and taking into account the relevant anthropometric characteristics of the person and the ergonomic, time and frequency parameters of work, for at least 3 years and at least 60 shifts per year. At the present time is used traditional certified method for work risk assessment which is based partly on the subjective assessment by a specialist in the field of occupational physiology. To replace this method a new ErgoVison, full-stack web-based application designed to automate ergonomic evaluations in industrial settings is tested. This system leverages advanced computer vision techniques to reconstruct a 3D representation of human posture from videos recorded with a single standard camera. By extracting key body joint angles—including spine angle and the distance to a handled weight—ErgoVision provides objective, quantifiable assessments that help ergonomists make rapid and reliable decisions. The ErgoVision web application streamlines video uploads, data processing, and reporting. The system designed to align with the ergonomic and legislative standards as defined by the Czech health government directives. Previous research in camera-based ergonomic assessments has largely focused on multi-camera setups. In contrast, this work is motivated by the need for a more accessible solution. By employing a single-camera approach combined with specialized reconstruction algorithms and a user-friendly web interface, ErgoVision seeks to democratize ergonomic assessments and offer a certified, objective evaluation tool for a broader audience. In the initial step, video footage is captured of a subject performing physical labor using a standard, single camera. The objective is to record high-quality visual data that accurately represents the subject's posture and movements during various tasks. This approach is designed to simplify the ergonomic evaluation process by leveraging readily available hardware, thereby reducing both cost and complexity in comparison to multi-camera setups. The accuracy of ergonomic assessment and its availability for industry is crucial in safeguarding worker´s health and optimizing productivity in industrial environments. Challenges such as the accurate reconstruction of extreme postures remain, highlighting avenues for future research. Ongoing developments will focus on refining the 3D reconstruction algorithms and expanding the system’s capabilities to accommodate a wider range of ergonomic scenarios. Ultimately, ErgoVision represents a significant step forward in automating ergonomic evaluations, with the promise of supporting informed interventions to improve worker safety and productivity. Future work will further explore integrating advanced sensor data and machine learning models to overcome current limitations, ensuring that the system remains adaptable to evolving ergonomic standards and industrial demands.ACKNOWLEDGMENT: Supported by Ministry of Health, Czech rep. - RVO (NIPH, 75010330).

Keywords: ergonomics, lumbar spine, work overload, occupational disease, 3D assessment, single camera

DOI: 10.54941/ahfe1006741

Cite this paper:

​