Geometric Compression of Orientation Signals for Fast Gesture Analysis

This paper concerns itself with compression strategies for orientation signals, seen as signals evolving on the space of quaternion´s. The compression techniques extend classical signal approximation strategies used in data mining, by explicitly taking into account the quotient-space properties of the quaternion space. The approximation techniques are applied to the case of human gesture recognition from cell phone-based orientation sensors. Results indicate that the proposed approach results in high recognition accuracies, with low storage requirements, with the geometric computations providing added robustness than classical vector-space computations.