Laser & Optoelectronics Progress, Volume. 59, Issue 2, 0215005(2022)

Fast Target Search Method Based on Feature Hierarchical Cascade Network

Haoyang Tang1, Cong Wu1, Yang Liu1、*, Yuxiang Zhai1, and Dongfang Yang2
Author Affiliations
  • 1Automation College, Xi'an University of Posts & Telecommunications, Xi'an , Shaanxi 710121, China
  • 2Missile Engineering College, Rocket Force University of Engineering, Xi'an , Shaanxi 710025, China
  • show less
    Figures & Tables(8)
    Flow chart of fast target search method based on feature hierarchical cascade network
    Legends of query and gallery. (a) Query; (b)-(e) gallerys
    Legends of bottom-level features extraction for local location. (a) Query; (b)-(e) gallerys
    Structure diagram of target re-identification network with hierarchical cascade features
    Examples of target re-identification datasets
    Visualization results of proposed algorithm
    • Table 1. Comparison of network speed and FLOPs

      View table

      Table 1. Comparison of network speed and FLOPs

      AlgorithmSpeed /(frame⋅s-1FLOPs
      Baseline7183.6
      Proposed algorithm1333.5
    • Table 2. Comparison of mAP of different algorithms

      View table

      Table 2. Comparison of mAP of different algorithms

      AlgorithmMarket1501DukeMTMC-reid
      Baseline86.176.4
      Proposed algorithm88.578.2
    Tools

    Get Citation

    Copy Citation Text

    Haoyang Tang, Cong Wu, Yang Liu, Yuxiang Zhai, Dongfang Yang. Fast Target Search Method Based on Feature Hierarchical Cascade Network[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0215005

    Download Citation

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

    Category: Machine Vision

    Received: Feb. 25, 2021

    Accepted: Apr. 14, 2021

    Published Online: Dec. 29, 2021

    The Author Email: Yang Liu (liuyang@xupt.edu.cn)

    DOI:10.3788/LOP202259.0215005

    Topics