Differences between motion capture and video analysis systems in calculating knee angles in elite-standard race walking

Race walking is an event where the knee must be straightened from first contact with the ground until midstance. The aim of this study was to compare knee angle measurements between 2D videography and 3D optoelectronic systems. Passive retroreflective markers were placed on the right leg of 12 race walkers and 3D marker coordinate data captured (250Hz), with 2D video data (100Hz) recorded simultaneously. Knee angle data were first derived based on the markers' coordinates, and separately by using a 3D model that also incorporated thigh and shank clusters; the video data were analysed using both automatic tracking and manual digitising, creating four conditions overall. Differences were calculated between conditions for stance (using root mean square values), and at discrete events. There were few differences between systems, although the 3D model produced larger angles at midstance than using automatic tracking and marker coordinates (by 3 - 6 degrees, P<0.05). These differences might have occurred because of how the 3D model locates the hip joint, and because of the addition of marker clusters. 2D videography gave similar results to the 3D model when using manual digitising, as it allowed for errors caused by skin movement to be corrected.