• Laser & Optoelectronics Progress
  • Vol. 59, Issue 18, 1815002 (2022)
Xuan He, Shuguo Pan*, Yong Tan, Wang Gao, and Hui Zhang
Author Affiliations
  • School of Instrument Science and Engineering, Southeast University, Nanjing 210096, Jiangsu, China
  • show less
    DOI: 10.3788/LOP202259.1815002 Cite this Article Set citation alerts
    Xuan He, Shuguo Pan, Yong Tan, Wang Gao, Hui Zhang. Visual-Inertial Odometry and Global Navigation Satellite System Location Algorithm Based on Point-Line Feature in Outdoor Scenes[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1815002 Copy Citation Text show less
    General framework of proposed algorithm
    Fig. 1. General framework of proposed algorithm
    Line feature extraction results and time consumption of each algorithm in measured environment. (a) Hough algorithm (118.045 ms); (b) LSD algorithm (62.7 ms); (c) LSWMS algorithm (40 ms); (d) EDLine algorithm (18.2 ms)
    Fig. 2. Line feature extraction results and time consumption of each algorithm in measured environment. (a) Hough algorithm (118.045 ms); (b) LSD algorithm (62.7 ms); (c) LSWMS algorithm (40 ms); (d) EDLine algorithm (18.2 ms)
    Possible changes in same line feature between two consecutive frames. (a) Existence of slight angles; (b) existence of slight distances
    Fig. 3. Possible changes in same line feature between two consecutive frames. (a) Existence of slight angles; (b) existence of slight distances
    Schematic diagram of coordinate frame involved in proposed system
    Fig. 4. Schematic diagram of coordinate frame involved in proposed system
    Platform for actual measurement data acquisition
    Fig. 5. Platform for actual measurement data acquisition
    Line feature matching results of traditional LSD algorithm and proposed algorithm. (a) LSD algorithm; (b) proposed algorithm
    Fig. 6. Line feature matching results of traditional LSD algorithm and proposed algorithm. (a) LSD algorithm; (b) proposed algorithm
    Trajectory fitting curves of KITTI data set experiments. (a) 09_30_0018 data set; (b) 09_30_0027 data set
    Fig. 7. Trajectory fitting curves of KITTI data set experiments. (a) 09_30_0018 data set; (b) 09_30_0027 data set
    APE root mean square error (APE_RMSE) comparison curves of KITTI data set experiments. (a) 09_30_0018 data set;
    Fig. 8. APE root mean square error (APE_RMSE) comparison curves of KITTI data set experiments. (a) 09_30_0018 data set;
    APE_RMSE comparison curves of tunnel data set experiments. (a) Tunnel 1 data set; (b) Tunnel 2 data set
    Fig. 9. APE_RMSE comparison curves of tunnel data set experiments. (a) Tunnel 1 data set; (b) Tunnel 2 data set
    Trajectory fitting curves of urban road data set experiment. (a) Urban road data set; (b) road of test field data set
    Fig. 10. Trajectory fitting curves of urban road data set experiment. (a) Urban road data set; (b) road of test field data set
    APE_RMSE comparison curves of urban road data set experiment. (a) Urban road data set; (b) road of test field data set
    Fig. 11. APE_RMSE comparison curves of urban road data set experiment. (a) Urban road data set; (b) road of test field data set
    SequenceVins_MonoPL-VIOVins_FusionProposed
    09_30_001820.4611.185.371.03
    09_30_002726.4123.323.660.74
    09_30_003322.8620.397.252.54
    09_30_003415.3126.784.620.68
    Table 1. Comparison of APE_RMSE of each algorithm in KITTI data set
    SequenceVins_MonoPL-VIOVins_FusionProposed
    Tunnel 186.2465.6273.6660.94
    Tunnel 270.1946.2664.6234.44
    Tunnel 3165.5396.06144.3270.56
    Table 2. Comparison of APE_RMSE of each algorithm in tunnel data set
    Urban roadRoad of test field
    APE_RMSE /mCompleteness /%APE_RMSE /mCompleteness /%
    SPP-92.86-84.00
    Vins_Mono206.73100.0098.19100.00
    PL-VIO151.42100.0082.58100.00
    Vins_Fusion99.90100.0063.09100.00
    Proposed3.10100.0014.72100.00
    Table 3. Positioning performance comparison of APE_RMSE of each algorithm in urban road data set
    OperationPL-VIO /msProposed /ms
    Point feature extraction and tracking7.8606.011
    Line feature extraction and tracking31.37627.219
    Line feature elimination0.0270.009
    Marginalization1.3261.192
    Table 4. Comparison of real-time performance of proposed algorithm with PL-VIO algorithm
    Xuan He, Shuguo Pan, Yong Tan, Wang Gao, Hui Zhang. Visual-Inertial Odometry and Global Navigation Satellite System Location Algorithm Based on Point-Line Feature in Outdoor Scenes[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1815002
    Download Citation