Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 55, Issue 2, 021002(2018)

Human Action Recognition Based on Quaternion 3D Skeleton Representation

Haiyang Xu1, Jun Kong1,2、*, and Min Jiang1
Author Affiliations
  • 1 School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China
  • 2 College of Electrical Engineering, Xinjiang University, Urumqi, Xinjiang 830047, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (9)
    Equations (0)
    References (22)
    Cited By (3)
    Tools
    Paper Information
    Topics
    Figures & Tables(9)
    Flow chart of training and testing process

    Fig. 1. Flow chart of training and testing process

    Download full size
    Hierarchical skeleton points and definition of skeletal vectors

    Fig. 2. Hierarchical skeleton points and definition of skeletal vectors

    Download full size
    (a) Representation of body part em in local coordinate system of en; (b) Representation of body part en in local coordinate system of em

    Fig. 3. (a) Representation of body part em in local coordinate system of en; (b) Representation of body part en in local coordinate system of em

    Download full size
    Angle cosine calculation between body parts

    Fig. 4. Angle cosine calculation between body parts

    Download full size
    Confusion matrix of MSR-Action3D database

    Fig. 5. Confusion matrix of MSR-Action3D database

    Download full size
    Confusion matrix of Florence3D-Action database

    Fig. 6. Confusion matrix of Florence3D-Action database

    Download full size

    • Table 1. Comparison of different descriptors different descriptors on MSR-Action3D dataset

      View table

      Table 1. Comparison of different descriptors different descriptors on MSR-Action3D dataset

      MethodRecognition rate /%
      Ref. [22]91.21*
      Ref. [10]92.03*
      Ref. [10]92.20*
      Ref. [17]92.49*
      Proposed95.17*
      Ref. [16]88.20
      Ref. [23]90.00
      Ref. [17]89.48
      Proposed91.88

    • Table 2. Recognition rate based on key frames on MSR-Action3D dataset

      View table

      Table 2. Recognition rate based on key frames on MSR-Action3D dataset

      MethodRecognition rate /%
      Quaternion withoutclassification of key frames94.12
      Quaternion withclassification of key frames95.17

    • Table 3. Comparison of different descriptors on database of UTKinect-Action and Florence3D-Action

      View table

      Table 3. Comparison of different descriptors on database of UTKinect-Action and Florence3D-Action

      DatasetMethodRecognition rate /%
      UTKinect-ActiondatasetRef. [22]88.50
      Ref. [24]94.50
      Ref. [17]97.08
      Proposed97.49
      Florence3D-Action datasetRef. [20]82.00
      Ref. [25]87.00
      Ref. [17]90.88
      Proposed92.14
    Tools

    Get Citation

    Copy Citation Text

    Haiyang Xu, Jun Kong, Min Jiang. Human Action Recognition Based on Quaternion 3D Skeleton Representation[J]. Laser & Optoelectronics Progress, 2018, 55(2): 021002

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Image processing

    Received: Jul. 19, 2017

    Accepted: --

    Published Online: Sep. 10, 2018

    The Author Email: Jun Kong (kongjun@jiangnan.edu.cn)

    DOI:10.3788/LOP55.021002

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology