北京航空航天大学学报 ›› 2019, Vol. 45 ›› Issue (12): 2495-2505.doi: 10.13700/j.bh.1001-5965.2019.0373

• 论文 • 上一篇    下一篇

面向行为识别的人体空间协同运动结构特征表示与融合

莫宇剑1, 侯振杰1, 常兴治2, 梁久祯1, 陈宸3, 宦娟1   

  1. 1. 常州大学 信息科学与工程学院, 常州 213164;
    2. 常州信息职业技术学院 智能制造工业云开放实验室, 常州 213164;
    3. 北卡罗来纳大学夏洛特分校 电气与计算机工程系, 夏洛特市 28223
  • 收稿日期:2019-07-09 出版日期:2019-12-20 发布日期:2019-12-31
  • 通讯作者: 侯振杰 E-mail:houzj@cczu.edu.cn
  • 作者简介:莫宇剑 男,硕士研究生。主要研究方向:机器学习、行为识别;侯振杰 男,博士,教授,硕士生导师。主要研究方向:机器学习、人工智能、图像处理。
  • 基金资助:
    国家自然科学基金(61063021,61803050);江苏省物联网移动互联技术工程重点实验室开放课题(JSWLW-2017-013)

Structural feature representation and fusion of behavior recognition oriented human spatial cooperative motion

MO Yujian1, HOU Zhenjie1, CHANG Xingzhi2, LIANG Jiuzhen1, CHEN Chen3, HUAN Juan1   

  1. 1. School of Information Science and Engineering, Changzhou University, Changzhou 213164, China;
    2. Open Lab of Industrial Cloud for Intelligent Manufacturing, Changzhou College of Information Technology, Changzhou 213164, China;
    3. Department of Electrical and Computer Engineering, University of North Carolina at Charlotte, Charlotte 28223, USA
  • Received:2019-07-09 Online:2019-12-20 Published:2019-12-31
  • Supported by:
    National Natural Science Foundation of China (61063021,61803050); Jiangsu Province Networking and Mobile Internet Technology Engineering Key Laboratory Open Research Fund Project (JSWLW-2017-013)

摘要: 针对人体执行动作时不同身体部位之间的协同关系,提出了基于人体空间协同运动结构特征的行为识别方法。首先度量人体不同部位对完成动作的贡献度,并将不同部位的贡献度转变为协同运动结构特征模型。然后利用模型无监督、自适应地对不同身体部位的运动特征进行约束。在此基础上借鉴跨媒体检索方法JFSSL对不同模态的特征进行特征选择与多模态特征融合。实验表明,所提方法在自建的行为数据库上明显提高了开放测试的识别率,且计算过程简便,易于实现。

关键词: 贡献度度量, 协同运动, 结构特征, 特征选择, 多模态融合

Abstract: In view of the synergistic relationship among different parts of the body when human body performs actions, a behavior recognition method based on human body spatial cooperative motion structural features is proposed. Firstly, the contribution of different parts of the human body to the completion of the action is measured, and the contribution of different parts of the human body is transformed into a structural feature model of cooperative motion. Then, the model is used to constrain the motion characteristics of different parts of the body self-adaptively without supervision. On this basis, feature selection and multi-modal feature fusion are carried out using JFSSL, a cross-media retrieval method. The experiments show that the recognition rate of the open test is obviously improved by the proposed method on the self-built behavior database. At the same time, the calculation process of the method is simple and easy to implement.

Key words: measure of contribution, cooperative motion, structural features, feature selection, multi-modal fusion

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发