VIDEO-BASED LIFTING TECHNIQUE CODING SYSTEM

Despite automation and improved-working conditions, many materials in industry are still handled manually. Among the basic activities involv ed in manual materials handling, lifting is the one most frequently as sociated with low-back pain (LBP). Biomechanical analysis techniques h ave been used to better understand the risk factors associated with ma nual handling, but because these techniques require specialized equipm ent, highly trained personnel, and interfere with normal business oper ations, they are limited in their usefulness. A video based lifting te chnique analysis system (the VidLiTeC(TM) System) is presented that pr ovides for quantifiable non-invasive biomechanical analysis of the dyn amic features of lifting with high inter-coder reliability and low sen sitivity to absolute errors. Analysis of results from a laboratory exp eriment and from field-collected videotape are described that support the reliability, sensitivity, and accuracy claims of the VidLiTeC(TM) System. The VidLiTeC(TM) System allows technicians with minimal traini ng and low-tech equipment (a camcorder) to collect large sets of lifti ng data without interfering with normal business operations. A reasona bly accurate estimate of the peak compressive force on the L5/S1 joint can be made from the data collected. Such a system can be used to col lect quantified data on lifting techniques that can be related to LBP reporting.