Behavioral Model Tracking of Hand Gestures

The paper presents an approach towards tracking and recognizing a set of predefined hand gestures from monocular image sequences. Firstly, a behavioral model of basic hand postures was depicted by mathematical expressions. Secondly, a behavioral model for hand posture tracking and hand posture tracking algorithm based on the behavioral model of hand postures were proposed. Finally, the proposed algorithm was compared and evaluated. Different from existing frame-based hand posture tracking, the proposed hand posture tracking targets at the tracking of users´ behavioral model within a certain period. It is innovative because: (1) it discloses the relationship between the operational model and behavioral model and verifies that the operation model can be predicted and evaluated, (2) it uses the operational model to describe the dynamic system model of hand postures. The experimental results confirm the satisfying performance of the proposed algorithm in improving the tracking time, tracking accuracy and cognition load evaluation.