Laser & Optoelectronics Progress, Volume. 56, Issue 18, 181501(2019)

Loop Closure Detection Algorithm Based on Convolutional Autoencoder Fused with Gist Feature

Chenli Qiu1,2, Dongzhen Huang1,2, Huawei Liu1, Xiaobing Yuan1, and Baoqing Li1、*
Author Affiliations
  • 1 Science and Technology on Microsystem Laboratory, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 201800, China
  • 2 University of Chinese Academy of Sciences, Beijing 100049, China
  • show less
    Figures & Tables(6)
    Training pairs with viewpoint change
    Training pipeline of convolutional autoencoder fused with Gist feature
    The flowchart of loop closure detection
    Some pictures from Gardens Point and Nordland test datasets. (a) Day_left; (b) day_right; (c) night_right; (d) spring sequence; (e) winter sequence
    Precision-recall curves for Gardens Point and Nordland datasets. (a) Gardens Point: day_left versus day_right; (b) Gardens Point: day_left versus night_right; (c) Nordland: spring versus winter
    • Table 1. Time to extracting features and querying the database on Gardens Point dataset

      View table

      Table 1. Time to extracting features and querying the database on Gardens Point dataset

      MethodExtract features time /msQuery time /μsComplexity /106
      Ours(GPU)0.815.88217.15
      CALC(GPU)0.645.13186.14
      Places-CNN(GPU)2.3142.98479.45
      BoVW(CPU)20.2717.00-
      Gist(CPU)41.435.10-
    Tools

    Get Citation

    Copy Citation Text

    Chenli Qiu, Dongzhen Huang, Huawei Liu, Xiaobing Yuan, Baoqing Li. Loop Closure Detection Algorithm Based on Convolutional Autoencoder Fused with Gist Feature[J]. Laser & Optoelectronics Progress, 2019, 56(18): 181501

    Download Citation

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

    Category: Machine Vision

    Received: Jan. 12, 2019

    Accepted: Apr. 9, 2019

    Published Online: Sep. 9, 2019

    The Author Email: Li Baoqing (sinoiot@mail.sim.ac.cn)

    DOI:10.3788/LOP56.181501

    Topics