Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (2): 454-457.DOI: 10.11772/j.issn.1001-9081.2017081945

Previous Articles     Next Articles

Human action recognition based on coupled multi-Hidden Markov model and depth image data

ZHANG Quangui, CAI Feng, LI Zhiqiang   

  1. School of Electronics and Information Engineering, Liaoning Technical University, Huludao Liaoning 125105, China
  • Received:2017-08-09 Revised:2017-09-09 Online:2018-02-10 Published:2018-02-10
  • Supported by:
    This work is partially supported by Liaoning Provincial Natural Science Foundation Project (2015020100).

基于耦合多隐马尔可夫模型和深度图像数据的人体动作识别

张全贵, 蔡丰, 李志强   

  1. 辽宁工程技术大学 电子与信息工程学院, 辽宁 葫芦岛 125105
  • 通讯作者: 蔡丰
  • 作者简介:张全贵(1978-),男,辽宁葫芦岛人,副教授,博士,CCF会员,主要研究方向:计算机视觉、机器学习、数据挖掘;蔡丰(1992-),女,辽宁大连人,硕士研究生,主要研究方向:计算机视觉;李志强(1993-),男,辽宁锦州人,硕士研究生,主要研究方向:计算机视觉、数据挖掘。
  • 基金资助:
    辽宁省自然科学基金面上项目(2015020100)。

Abstract: In order to solve the problem that the feature extraction is easy to be affected by external factors and the computational complexity is high, the depth data was used for human action recognition, which is a more effective solution scheme. Using the joint data collected by Kinect, the human joint was divided into five regions. The vector angle of each region was discretized to describe different states, and then Baum-Welch algorithm was used to study multi-Hidden Markov Model (multi-HMM), meanwhile, forward algorithm was used to establish the generation region and action class probability matrix. On this basis, the region and action categories were intra-coupled and inter-coupled to analyze, thus expressing the interaction between the joints. Finally, the K-Nearest Neighbors (KNN) algorithm based on coupling was used to complete the action recognition. The experimental results show that the recognition rates of the five actions reach above 90%, and the comprehensive recognition rate is higher than that of the contrast methods such as 3D Trajecttories, which means that the proposed algorithm has obvious advantages.

Key words: Kinect, human action recognition, divide area, multi-HMM (multi-Hidden Markov Model), coupled K-Nearest Neighbors (KNN)

摘要: 为解决使用RGB图像进行特征提取时容易受外界因素干扰,且计算复杂度高等问题,采用一种更加有效的解决方案,即使用深度数据进行人体动作识别。利用Kinect采集的关节点数据,首先将人体关节划分成五个区域,对每个区域的向量夹角离散化从而描述不同的状态,再通过Baum-Welch算法学习出各区域的多隐马尔可夫模型(multi-HMM),并使用前向算法建立生成区域与动作类别概率矩阵。在此基础上,对区域及动作类别进行内耦合和间耦合分析,从而表达各关节点之间的交互关系。最后使用基于耦合的K最邻近(KNN)算法完成整体的动作识别。通过实验测试对五种动作的识别率均达到90%以上,并与3D Trajectories等方法进行对比,实验得到的综合识别率高于对比方法,具有明显的优势。

关键词: Kinect, 人体动作识别, 划分区域, 多隐马尔可夫模型, 耦合K最邻近

CLC Number: