Laser & Optoelectronics Progress, Volume. 57, Issue 2, 21004(2020)

Human Action Recognition Based on Global and Local Features

Liu Fan* and Yu Fengqin
Author Affiliations
  • School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China
  • show less
    Figures & Tables(5)
    Flow chart of algorithm
    SURF extraction
    Comparison of HOG features before and after improvement
    Recognition accuracies of proposed algorithm in different datasets. (a) Confusion matrix on KTH dataset; (b) confusion matrix on UCF Sports dataset; (c) confusion matrix on SBU Kinect Interaction dataset
    • Table 1. Recognition accuracies of different methods

      View table

      Table 1. Recognition accuracies of different methods

      Methodη on KTH /%Methodη on UCF sports /%Methodη on SBU Kinect Interaction /%
      Method in Ref. [16]95.6Ref. [16]88.5Ref. [15]80.3
      Method in Ref. [17]95.6Ref. [18]92.7Ref. [22]89.4
      Method in Ref. [18]Method in Ref. [19]Proposed method96.897.896.7Ref. [20]Ref. [21]Proposed95.897.594.4Ref. [23]Ref. [24]Proposed94.898.590.8
    Tools

    Get Citation

    Copy Citation Text

    Liu Fan, Yu Fengqin. Human Action Recognition Based on Global and Local Features[J]. Laser & Optoelectronics Progress, 2020, 57(2): 21004

    Download Citation

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

    Category: Image Processing

    Received: May. 5, 2019

    Accepted: --

    Published Online: Jan. 3, 2020

    The Author Email: Liu Fan (977216218@qq.com)

    DOI:10.3788/LOP57.021004

    Topics