Surface Prediction for Spatial Augmented Reality Using Cubature Kalman Filtering

Projection mapping onto non-rigid deformable objects requires highly accurate tracking of its surface position. Traditional methods of using measured deformations of the surface can be inadequate due to potential sources of time delay, such as projector lag. Previous work done by Gomes et al. [3] demonstrated a novel approach for predicting the motion of a non-rigid surface to assist in the compensation of any delays. This paper improves upon the extended Kalman filter algorithm, presented by Gomes et al., by introducing a higher order approximation using the cubature Kalman filter. This algorithm is verified using an experimental setup where an image is projected onto a deformable surface being disturbed by a "random" force. The results show a marked improvement over the extended Kalman filter. The error results demonstrate that the cubature Kalman filter can be applied to situations with low measurement capture rates as well as higher levels of occlusion.