A Neural Network Approach to Missing Marker Reconstruction in Human Motion Capture
This addresses a practical issue in fields like augmented reality and robotics by enabling real-time marker reconstruction, though it is incremental as it builds on existing neural network methods.
The paper tackles the problem of missing marker reconstruction in optical motion capture systems by using neural networks to learn temporal and spatial correlations in human motion, achieving state-of-the-art results with online processing capabilities.
Optical motion capture systems have become a widely used technology in various fields, such as augmented reality, robotics, movie production, etc. Such systems use a large number of cameras to triangulate the position of optical markers.The marker positions are estimated with high accuracy. However, especially when tracking articulated bodies, a fraction of the markers in each timestep is missing from the reconstruction. In this paper, we propose to use a neural network approach to learn how human motion is temporally and spatially correlated, and reconstruct missing markers positions through this model. We experiment with two different models, one LSTM-based and one time-window-based. Both methods produce state-of-the-art results, while working online, as opposed to most of the alternative methods, which require the complete sequence to be known. The implementation is publicly available at https://github.com/Svito-zar/NN-for-Missing-Marker-Reconstruction .