We are developing video processing algorithms for automatically measuring the ACGIH TLV® handactivity level (HAL) using marker-less tracking of hand movements. An equation for computing HALratings directly from tracked kinematics, rather than using a frequency-duty cycle (DC) look-up table, morereadily lends itself to automated processing. Videos from the 33 Latko et al. (1997) jobs were digitized andanalyzed using marker-less tracking, and hand root mean square (RMS) speed (S) was measured. A linearregression model was developed for predicting the average observer rated HAL based on the measuredhand RMS speed and DC. Since the videos did not contain distance calibration, speed was quantified inpixels/s and normalized by the distance of each worker’s hand breadth, measured in pixels. A Monte Carlosimulation was performed using the US Army (1991) hand anthropometry data to determine how variationis introduced in the equation as hand breadth varies. The resulting equation was HAL= −1.06 + 0.0047 S +0.053 DC and it predicted HAL ratings within ±1. The development of an accurate equation for estimatingHAL ratings should enable use of automated and objective measurement in practice. While expert observerHAL ratings offer speed and efficiency, use of objective measurements based on worker hand kinematicsshould provide greater reliability, as well as offering specific engineering aspects of the job that may beaddressed for reducing exposures and the risk of musculoskeletal disorders. Furthermore, automatedvideos analysis may help improve the speed and efficiency of making objective measurements in practice.
展开▼