• 综合性科技类中文核心期刊
    • 中国科技论文统计源期刊
    • 中国科学引文数据库来源期刊
    • 中国学术期刊文摘数据库(核心版)来源期刊
    • 中国学术期刊综合评价数据库来源期刊

基于人体手臂关节信息的非接触式手势识别方法

于乃功, 王锦

于乃功, 王锦. 基于人体手臂关节信息的非接触式手势识别方法[J]. 北京工业大学学报, 2016, 42(3): 361-368. DOI: 10.11936/bjutxb2015060061
引用本文: 于乃功, 王锦. 基于人体手臂关节信息的非接触式手势识别方法[J]. 北京工业大学学报, 2016, 42(3): 361-368. DOI: 10.11936/bjutxb2015060061
YU Naigong, WANG Jin. Non-contact Gesture Recognition Method Based on the Information of the Human Arm Joint[J]. Journal of Beijing University of Technology, 2016, 42(3): 361-368. DOI: 10.11936/bjutxb2015060061
Citation: YU Naigong, WANG Jin. Non-contact Gesture Recognition Method Based on the Information of the Human Arm Joint[J]. Journal of Beijing University of Technology, 2016, 42(3): 361-368. DOI: 10.11936/bjutxb2015060061

基于人体手臂关节信息的非接触式手势识别方法

基金项目: 

国家自然科学基金资助项目(61375086)

详细信息
    作者简介:

    于乃功(1966—),男,教授,主要从事人工智能与机器学习方面的研究,E-mail:yunaigong@bjut.edu.cn

  • 中图分类号: U461;TP308

Non-contact Gesture Recognition Method Based on the Information of the Human Arm Joint

  • 摘要: 为了实现在复杂环境中对连续动态手势的识别,以人体固有的手臂关节之间的约束关系及特定手势在三维空间的运动轨迹为特征,提出了一种非接触式手势识别方法.首先,通过Kinect传感器获取人体手臂关节的三维数据;然后,对手势轨迹进行分割,并将具有三维空间特征的手势轨迹转化为一维的手势轨迹;最后,将手势预判断过程与改进的动态时间规整(dynamic time warp,DTW)算法相结合,实现对动态手势的快速高效识别.实验结果表明:该方法对具有时空连续特征的动态手势识别率较高,在复杂背景和不同光照环境中都有较强的鲁棒性.
    Abstract: To realize the continuous and dynamic gesture recognition in complex environment, an approach for non-contact hand gesture recognition method was proposed by using the inherent constraint relationship in the arm joints and the specific gesture track characteristics in three-dimensional space.First,a three-dimensional data of human arm joints from the Kinect sensor was obtained. Then,the gesture track with the three-dimensional space characteristics was segmented and converted to onedimensional gesture track. Finally,gesture to preliminary judgment process with the improved dynamic time warp( DTW) algorithm was combined to achieve fast and efficient recognition of dynamic gestures.The experimental results show that the method of gesture track with the space-time characteristics has a high recognition rate and strong robustness under different light and complicated backgrounds.
  • [1] 陶丽君,李翠华,张希婧.基于Kinect传感器深度信息的动态手势识别[J].厦门大学学报(自然科学版),2013,52(4):493-497.

    TAO L J,LI C H,ZHANG X J.Dynamic gesture recognition based on depth information of Kinect sensor[J].Journal of Xiamen University(Nature Science Edition),2013,52(4):493-497.

    [2] 陈皓,路海明.基于深度图像的手势识别综述[J].内蒙古大学学报(自然科学版),2014,45(1):105-111.

    CHEN H,LU H M.Gesture recognition based on depth image review[J].Journal of Inner Mongolia University(Nature Science Edition),2014,45(1):105-111.

    [3] 毛雁明,章立亮.基于Kinect深度信息的手势分割与识别[J].系统仿真学报,2015(4):830-835.

    MAO Y M,ZHANG L L.Gesture segmentation and recognition based on the depth information[J].Journal of System Simulation,2015(4):830-835.

    [4] 淦创.基于3D体感技术的动态手势识别[J].光电技术应用,2012,27(4):55-58.

    GAN C.Dynamic gesture recognition based on 3D motionsensing technology[J].Photoelectric Technology Application,2012,27(4):55-58.

    [5] 刘贤梅,赵丹,郝爱民.基于优化的DTW算法的人体运动数据检索[J].模式识别与人工智能,2012,25(2):352-360.

    LIU X M,ZHAO D,HAO A M.Human movement data retrieval based on DTW algorithm of optimization[J].Journal of Pattern Recognition and Artificial Intelligence,2012,25(2):352-360.

    [6]

    WU J,KONRAD J,ISHWAR P.Dynamic time warping for gesture-based user identification and authentication with kinect[C]∥2013 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).Piscataway,NJ:IEEE,2013:2371-2375.

    [7] 荆雷,马文君,常丹华.基于动态时间规整的手势加速度信号识别[J].传感技术学报,2012,25(1):72-76.

    JING L,MA W J,CHANG D H.Gestures acceleration signal recognition based on dynamic time warp[J].Journal of Sensing Technology,2012,25(1):72-76.

    [8]

    SEMPENA S,MAULIDEVI N U,ARYAN P R.Human action recognition using dynamic time warping[C]∥Electrical Engineering and Informatics(ICEEI),2011International Conference on IEEE.Piscataway,NJ:IEEE,2011:1-5.

    [9]

    CHEN L,WEI H,FERRYMAN J.A survey of human motion analysis using depth imagery[J].Pattern Recognition Letters,2013,34(15):1995-2006.

    [10]

    AY B,KARAKOSE M.Motion classification approach based on biomechanical analysis of human activities[C]∥Computational Intelligence and Computing Research(ICCIC),2013 IEEE International Conference on.Piscataway,NY:IEEE,2013:1-8.

    [11] 冯志远,张连海.基于分段动态时间规整的语音样例快速检索[J].数据采集与处理,2014,29(2):265-273.

    FENG Z Y,ZHANG L H.Speech sample fast retrieval based on dynamic time warp[J].Journal of Data Acquisition and Processing,2014,29(2):265-273.

    [12]

    LEE J H,KIM H K,NAM S W,et al.Application adaptation methods of gesture recognition based user interface[C]∥The 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision.Piscataway,NY:IEEE,2013:258-261.

    [13] 李瑞峰,曹雏清,王丽.基于深度图像和表观特征的手势识别[J].华中科技大学学报(自然科学版),2011,39(增刊2):88-91.

    LI R F,CAO C Q,WANG L.Gesture recognition based on depth image and apparent features[J].Journal of Huazhong University of Science and Technology(Nature Science Edition),2011,39(Suppl 2):88-91.

计量
  • 文章访问数:  8
  • HTML全文浏览量:  0
  • PDF下载量:  6
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-06-18
  • 网络出版日期:  2023-01-10

目录

    /

    返回文章
    返回