• Acta Optica Sinica
  • Vol. 37, Issue 11, 1115001 (2017)
Zhilin Lin, Guoliang Zhang*, Erliang Yao, and Hui Xu
Author Affiliations
  • Department of Control Science and Engineering, Rocket Force Engineering University, Xi'an, Shaanxi 710025, China
  • show less
    DOI: 10.3788/AOS201737.1115001 Cite this Article Set citation alerts
    Zhilin Lin, Guoliang Zhang, Erliang Yao, Hui Xu. Stereo Visual Odometry Based on Motion Object Detection in the Dynamic Scene[J]. Acta Optica Sinica, 2017, 37(11): 1115001 Copy Citation Text show less
    Schematic of generating the virtual map points
    Fig. 1. Schematic of generating the virtual map points
    (a) Schematic of the object motion vector angle; (b) corresponding result of GMM
    Fig. 2. (a) Schematic of the object motion vector angle; (b) corresponding result of GMM
    Diagram of the algorithm
    Fig. 3. Diagram of the algorithm
    Results of motion object detection
    Fig. 4. Results of motion object detection
    Schematic of local map
    Fig. 5. Schematic of local map
    Results of the contrast experiment on TUM dataset
    Fig. 6. Results of the contrast experiment on TUM dataset
    Bumblebee2 stereo camera
    Fig. 7. Bumblebee2 stereo camera
    Route of the moving person
    Fig. 8. Route of the moving person
    Results of online experiment based on ORB-SLAM2 method. (a) Estimated trajectory of camera; (b) error of the estimated position of camera; (c)-(h) image frames and poses of camera corresponding to position A-F
    Fig. 9. Results of online experiment based on ORB-SLAM2 method. (a) Estimated trajectory of camera; (b) error of the estimated position of camera; (c)-(h) image frames and poses of camera corresponding to position A-F
    Results of online experiment based on proposed algorithm. (a) Estimated trajectory of camera; (b) error of the estimated position of camera; (c)-(h) image frames and poses of camera corresponding to position A-F
    Fig. 10. Results of online experiment based on proposed algorithm. (a) Estimated trajectory of camera; (b) error of the estimated position of camera; (c)-(h) image frames and poses of camera corresponding to position A-F
    OperationORB extractionPose initiationMODTrack LTrack VTotal
    Time /ms10.923.441.2716.312.5034.44
    Table 1. Run time of the contrast experiments on dataset
    MethodORB-SLAM2 methodProposed algorithm
    Sitting_xyz0.0099210.010144
    Sitting_halfsphere0.0211150.023901
    Sitting_rpy0.0220080.018039
    Sitting_static0.0082940.008146
    Walking_xyz0.4266400.225116
    Walking_halfsphere0.4479230.042330
    Walking_rpy0.7407740.196101
    Walking_static0.1028370.012093
    Table 2. Results of the contrast experiment
    Zhilin Lin, Guoliang Zhang, Erliang Yao, Hui Xu. Stereo Visual Odometry Based on Motion Object Detection in the Dynamic Scene[J]. Acta Optica Sinica, 2017, 37(11): 1115001
    Download Citation