计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (17): 195-197.

• 图形、图像、模式识别 • 上一篇    下一篇

基于腿部三角特征的贝叶斯步态识别方法

李熙熙,李 宏   

  1. 中南大学 信息科学与工程学院,长沙 410083
  • 收稿日期:2007-09-14 修回日期:2007-12-17 出版日期:2008-06-11 发布日期:2008-06-11
  • 通讯作者: 李熙熙

New method of gait recognition using Bayesian based on triangle feature of human leg

LI Xi-xi,LI Hong   

  1. School of Information Science and Engineering,Central South University,Changsha 410083,China
  • Received:2007-09-14 Revised:2007-12-17 Online:2008-06-11 Published:2008-06-11
  • Contact: LI Xi-xi

摘要: 提出了一种基于步态序列中腿部三角特征的步态表示方法,在这种特征上用改进的朴素贝叶斯分类方法进行步态识别。选取步幅最大、最小两种情况下的姿态作为关键帧,用三角型模拟其腿部特征,提取三角型模型参数作为步态特征,识别时先分别用KNN和一种改进的N-best取得属性值在训练数据中的对应数值,然后用贝叶斯分类方法识别。在NLPR数据库上使用留一校验方法进行算法验证,实验证明该方法简单快速,而且取得了比较理想的识别效果。

Abstract: This paper introduces a new method of gait representation and an improved Bayesian classification algorithm based on it at the same time.A triangle is applied to simulate the legs of key frame which has the maximal or minimal step,and extracts its parameters as the gait feature.KNN and a new N-best algorithm are used for test-data search the optimal numerical value from training data before Bayesian classification.The experimental results on the NLRP database show that the new method is not only simple and fast but also effective.