计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3441-3445.

• 人工智能 • 上一篇    下一篇

基于Kinect骨骼预定义的体态识别算法

张丹1,陈兴文1,赵姝颖2,李纪伟2,白钰3   

  1. 1. 大连民族学院 创新教育中心,辽宁 大连 116600
    2. 东北大学 信息科学与工程学院,沈阳 110819;
    3. 大连民族学院 信息与通信工程学院,辽宁 大连 116600
  • 收稿日期:2014-06-27 修回日期:2014-09-10 出版日期:2014-12-01 发布日期:2014-12-31
  • 通讯作者: 张丹
  • 作者简介:张丹(1987-),女,辽宁大连人,工程师,硕士,主要研究方向:图像处理、机器视觉;陈兴文(1969-),男,辽宁大连人,教授,主要研究方向:图像处理、模式识别;赵姝颖(1968-),女,辽宁沈阳人,教授,博士,主要研究方向:图像处理、计算机视觉;李纪伟(1987-),男,河南郑州人,工程师,主要研究方向:计算机视觉、人机交互。
  • 基金资助:

    中央高校基础科研基金资助项目;机器人学国家重点实验室开放基金资助项目

Posture recognition method based on Kinect predefined bone

ZHANG Dan1,CHEN Xingwen1,ZHAO Shuying2,LI Jiwei2,BAI Yu3   

  1. 1. Innovation Education Center, Dalian Nationalities University, Dalian Liaoning 116600,China;
    2. College of Information Science and Engineering, Northeastern University, Shenyang Liaoning 110819, China;
    3. College of Information and Communication Engineering, Dalian Nationalities University, Dalian Liaoning 116600, China
  • Received:2014-06-27 Revised:2014-09-10 Online:2014-12-01 Published:2014-12-31
  • Contact: ZHANG Dan

摘要:

针对基于视觉的体态识别对环境要求较高、抗干扰性差等问题,提出了一种基于人体骨骼预定义的识别分类方法。该算法结合Kinect多尺度深度信息和梯度信息检测人体;基于随机森林采用正负样本互限思想识别人体各个部分,根据各部分距离构建人体姿态向量,识别骨架;再根据体态类别,构建最优分类超平面、核函数,采用改进的支持向量机进行体态分类。实验结果表明,所提算法的分类识别准确率可达94.3%,具有实时性好,抗干扰性强,鲁棒性较好等特点。

Abstract:

In view of the problems that posture recognition based on vision requires a lot on environment and has low anti-interference capacity, a posture recognition method based on predefined bone was proposed. The algorithm detected human body by combining Kinect multi-scale depth and gradient information. And it recognized every part of body based on random forest which used positive and negative samples, built the body posture vector. According to the posture category, optimal separating hyperplane and kernel function were built by using improved support vector machine to classify postures. The experimental results show that the recognition rate of this scheme is 94.3%, and it has good real-time performance, strong anti-interference, good robustness, etc.

中图分类号: