Extension limb action recognition based on acceleration median

  • Authors:

  • Yonghua Wang;Lei Qi;Fei Yuan;Jian Yang

  • Affiliations:

  • Faculty of Automation, Guangdong University of Technology, Guangzhou, China;Center of Campus Network&Modem Educational Technology, Guangdong University of Technology, Guangzhou, China;School of Information Science and Technology, Sun Yat-sen University, Guangzhou, China;Faculty of Automation, Guangdong University of Technology, Guangzhou, China

  • Venue:
  • ICICA'11 Proceedings of the Second international conference on Information Computing and Applications
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

An extension limb action recognition method based on acceleration median (EULAR-AM) is proposed in this paper. Stretch arm has the feature that the arm's acceleration increases firstly, and then decreases. So the EULAR-AM chooses the acceleration median of the arm outstretching process and the direction of acceleration at the initial moment of arm outstretching as its recognition characteristic values. It can reduce the affection of outstretching speed to the characteristic value of limb action, and can achieve the goal that the different outstretching speed actions having same direction could be described by the same characters. Then combining the extension recognition method, the EULAR-AM recognized the limb action. The experiment results show that the recognition accuracy rate of the EULAR-AM is 93.2 %.