A 3D Motion Trajectory Signature Identification for Human- Computer Interaction (HCI) Applications

Trajectory tracking is used to keep tracks objects. Trajectory tracking control is used to affect desired trajectories of a device, human and anything can move. In order to precisely track specified trajectories, or be able to follow more general trajectories, many tracking control algorithms have been proposed, but still there is some problems of tracking trajectory in its application. This paper introduces a new model for trajectory signature tracking that integrates the maximally stability extremal regions (MSER) feature extraction of first level transformed domain descriptors with Knearest neighbour classifier. Experiments have been carried out on large datasets of tracking trajectories with different characteristics. MATLAB software version R2013a is used to implement and test the proposed method. Experimental Results showed that the proposed model produces satisfactory performance. Significant improvements have been illustrated in terms of recognition rate and recognition efficiency.