A practical computer based vision system for posture and movement sensing in occupational medicine

Back pain and upper extremities injuries due to overexertion account for over twenty percent of leave days from work in the US. This explains why a vast amount of initiatives have been, to this date, carried out aiming at reducing the occurrence of such type of injuries. However, although such type of lesions are among the most studied in occupational medicine, no automatic detection and prevention technologies are pervasively available, to this date, at workplaces. Such deficiency is ascribable to the absence of any flexible and cost-effective tectaphnology that may play such role. This work aims at filling such gap: the contribution of this paper is the design and implementation of a movement-posture computer-vision based system that, performing as a sensor, can detect overexertion movements, helping avoid the most common injuries that these cause. Such tasks are carried out with the use of a simple webcam, thus not requiring any expensive or specialized (e.g., Microsoft Kinect) hardware device. The proposed technology is, hence, easily affordable by any type of company and production plant throughout the world and easy adaptable to recognize and detect a wide set of movements and postures. The validity of such approach is demonstrated in realistic settings through a wide set of experiments