Towards Solving the Missing Marker Problem in Realtime Motion Capture

A common problem in optical motion capture is the so-called missing marker problem. The occlusion of markers can lead to significant loss of tracking accuracy unless continuous data flow is guaranteed by computationally demanding interpolation or extrapolation schemes. Since interpolation algorithms require data sampled before and after an occlusion, they cannot be used for real-time applications. Extrapolation algorithms only require data sampled before an occlusion. Other algorithms require statistical data and are designed for post-processing. In order to bridge sampling gaps caused by occluded markers and hence to improve 3D real-time motion capture, we suggest a real-time extrapolation algorithm. The realization of this prediction algorithm does not need statistical data or rely on an underlying cinematic human model with pre-defined marker distances. Under the assumption that natural motion can be linear, circular, or a linear combination of both, a prediction method is suggested and realized. The paper presents linear and circular movement measurements for use when a marker is briefly lost. The suggested extrapolation method seems to behave well for a reasonable number of frames, not exceeding 200 milliseconds.