Date(s) - February 21, 2020
11:45 am - 12:35 pm
406 Weil Hall
Robert G. Radwin, Ph.D., CPE
Duane H. and Dorothy M. Blumke Professor
University of Wisconsin-Madison
Abstract: Computer Vision Technology for Evaluating Risk of Occupational Injuries
Repetitive motion injuries in the workplace impose a significant socioeconomic burden and substantial personal toll on health, prosperity and wellbeing. Manual lifting is an important occupational health and safety concern and is highly prevalent in warehousing, distribution centers, package delivery, transportation, and lean manufacturing. For prevention of work-related injuries, it has therefore become increasingly important to frequently or continuously monitor workers’ exposure to physical demands for varying job tasks. Practical methods for evaluating these types of jobs are currently unavailable, and safety practitioners may not have the resources to observe lifting continuously in numerous locations. Consequently, many hazardous jobs remain unresolved or unrecognized until an injury occurs, resulting in unrecoverable losses to both employers and employees. We are using computer vision and machine learning algorithms for automatically, objectively, and unobtrusively measuring repetitive motion and manual lifting activities. These methods have the potential to be implemented on hand-held devices, such as smartphones, making it widely accessible.