Laser & Optoelectronics Progress, Volume. 56, Issue 24, 241504(2019)

Hybrid Tracking Registration of Augmented Reality Based on Salience Detection

Fanyi Gao1,2, Jianwu Dang1,2、*, and Yangping Wang1,2、**
Author Affiliations
  • 1School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, China
  • 2Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics & Image Processing, Lanzhou, Gansu 730070, China;
  • show less
    Figures & Tables(10)
    Overall framework of mixed tracking registration algorithm
    Simulation results of salience combined with center prior. (a) Original image; (b) global salience map; (c) salience map with center prior
    Schematics of feature extraction. (a) FAST feature detection; (b) BRIEF feature descriptor
    Schematic of feature matching. (a) Hamming distance matching; (b) eliminating mismatches
    Tracking results of different algorithms. (a) Box sequence; (b) Liquor sequence
    Central position errors of different algorithms. (a) Box sequence; (b) Liquor sequence
    Tracking registration results of Box sequence. (a) ORB feature and optical flow method; (b) proposed method
    Tracking registration results of Liquor sequence. (a) ORB feature and optical flow method; (b) proposed method
    • Table 1. Average central errors of different algorithmspixel

      View table

      Table 1. Average central errors of different algorithmspixel

      Data setPFASMSSTCLKOurs
      Box146.1110061.0696065.7324023.979907.85212
      Liquor38.5954027.2565016.2262070.193606.51653
    • Table 2. Comparison of average tracking speeds of different algorithmsframe/s

      View table

      Table 2. Comparison of average tracking speeds of different algorithmsframe/s

      Data setPFASMSSTCLKOurs
      Box4.233.228.539.823.1
      Liquor7.131.832.740.226.4
    Tools

    Get Citation

    Copy Citation Text

    Fanyi Gao, Jianwu Dang, Yangping Wang. Hybrid Tracking Registration of Augmented Reality Based on Salience Detection[J]. Laser & Optoelectronics Progress, 2019, 56(24): 241504

    Download Citation

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

    Category: Machine Vision

    Received: Apr. 29, 2019

    Accepted: Jun. 13, 2019

    Published Online: Nov. 26, 2019

    The Author Email: Dang Jianwu (dangjw@mail.lzjtu.cn), Wang Yangping (13519311970@163.com)

    DOI:10.3788/LOP56.241504

    Topics