Journal of Applied Sciences ›› 2017, Vol. 35 ›› Issue (1): 81-89.doi: 10.3969/j.issn.0255-8297.2017.01.009

• Signal and Information Processing • Previous Articles     Next Articles

Gesture Tracking Using Improved Linear Extrapolation Predictor

YAO Heng, YUAN Min, QIN Chuan, TIAN Ying   

  1. Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
  • Received:2016-03-28 Revised:2016-04-12 Online:2017-01-30 Published:2017-01-30

Abstract:

To improve accuracy of gesture tracking in dynamic gesture recognition system, a gesture tracking algorithm using an improved linear extrapolation predictor is proposed.Specifcally, to improve prediction accuracy, the algorithm uses the average displacement of two previous frames as the future-frame predictor.Besides, to deal with occlusion and hands-overlap, the target movement direction is determined based on the slope of ftting line with fve points.Thus deviation between the predicted and actual positions caused by the changing gesture centroid is reduced.Experimental results show that efciency of the proposed gesture tracking method with the average prediction deviation is reduced to 3.374 pixels.In addition, even in the case of occlusion and hands-overlap, the gesture target can also be tracked effectively.

Key words: gesture tracking, linear extrapolation, dynamic gesture recognition system, gesture occlusion and overlap

CLC Number: