Examination of 2D frontal and sagittal markerless motion capture: Implications for 2D and 3D markerless applications

This study examined if occluded joint locations from markerless motion capture produced 2D joint angles with reduced accuracy compared to visible joints, and if 2D frontal plane joint angles were usable for practical applications. Fifteen healthy participants performed over-ground walking whilst recorded by fifteen marker-based cameras and two machine vision cameras (frontal and sagittal plane). Repeated measures Bland-Altman analysis illustrated that markerless standard deviation of bias (random differences) for the occluded-side hip and knee joint angles in the sagittal plane were double that of the camera-side (visible) hip and knee. Camera-side sagittal plane knee and hip angles were near or within marker-based error values previously observed. While frontal plane random differences accounted for 35-46% of total range of motion at the hip and knee, systematic and random differences (-4.6-1.6 {+/-} 3.7-4.2{degrees}) were actually similar to previously reported marker-based error values. This was not true for the ankle, where random difference ({+/-}12{degrees}) was still too high for practical applications. Our results add to previous literature, highlighting shortcomings of current pose estimation algorithms and labelled datasets. As such, this paper finishes by reviewing marker-based methods for creating anatomically accurate markerless training data.