3D Model-Based Hand Tracking

Hand tracking has great potential as a tool for better human-computer interaction. Areas of application include navigation in virtual environments, gesture recognition and motion capture for film animation. This report presents a new method for 3D hand tracking. It uses a 3D model built from truncated quadrics which approximates the anatomy of a real human hand. This approach allows for the use of results from projective geometry that yield an elegant technique to generate the projection of the model as a set of conics, as well as providing an efficient algorithm to handle self-occlusion. Once the model is projected, an Unscented Kalman filter is used to update its pose in order to minimise the geometric error between the projected contour of the model and a video sequence on the background. Results from experiments with real data show the accuracy of the technique.