Abstract
Marker-based motion capture systems using infrared cameras (IR MoCaps) are commonly employed in biomechanical research. However, their high costs pose challenges for many institutions seeking to implement such systems. This study aims to develop a neural network (NN) model to estimate the digitized coordinates of spherical markers and to establish a lower-cost marker-based motion capture system using RGB cameras. Thirteen participants were instructed to walk at self-selected speeds while their movements were recorded with eight RGB cameras. Each participant undertook trials with 24 mm spherical markers attached to 25 body landmarks (marker trials), as well as trials without markers (non-marker trials). To generate training data, virtual markers mimicking spherical markers were randomly inserted into images from the non-marker trials. These images were then used to fine-tune a pre-trained model, resulting in an NN model capable of detecting spherical markers. The digitized coordinates inferred by the NN model were employed to reconstruct the three-dimensional coordinates of the spherical markers, which were subsequently compared with the gold standard. The mean resultant error was determined to be 2.2 mm. These results suggest that the proposed method enables fully automatic marker reconstruction comparable to that of IR MoCap, highlighting its potential for application in motion analysis.