• Laser & Optoelectronics Progress
  • Vol. 57, Issue 16, 161011 (2020)
Hong Yang1、2 and Aijun Xu1、2、3、*
Author Affiliations
  • 1School of Information Engineering, Zhejiang A & F University, Hangzhou, Zhejiang 311300, China;
  • 2Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology, Zhejiang A & F University, Hangzhou, Zhejiang 311300, China;
  • 3Key Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Engineering, Zhejiang A & F University, Hangzhou, Zhejiang 311300, China;
  • show less
    DOI: 10.3788/LOP57.161011 Cite this Article Set citation alerts
    Hong Yang, Aijun Xu. Tree Depth Image Generation Algorithm Based on Short Video Images[J]. Laser & Optoelectronics Progress, 2020, 57(16): 161011 Copy Citation Text show less
    Schematic of proposed algorithm
    Fig. 1. Schematic of proposed algorithm
    s-t network
    Fig. 2. s-t network
    Segmentation results of tree image. (a) Before segmentation; (b) after segmentation
    Fig. 3. Segmentation results of tree image. (a) Before segmentation; (b) after segmentation
    Tree feature points
    Fig. 4. Tree feature points
    D-U radial distortion model
    Fig. 5. D-U radial distortion model
    Schematic of plane scanning method
    Fig. 6. Schematic of plane scanning method
    Schematic of camera motion trajectory. (a) Reference frame; (b) stacking of each frame; (c) details
    Fig. 7. Schematic of camera motion trajectory. (a) Reference frame; (b) stacking of each frame; (c) details
    Segmentation of tree image and extraction of feature points. (a) Reference frame; (b) feature points before segmentation; (c) feature points after segmentation
    Fig. 8. Segmentation of tree image and extraction of feature points. (a) Reference frame; (b) feature points before segmentation; (c) feature points after segmentation
    Focal length values after bundle adjustment withdifferent feature points
    Fig. 9. Focal length values after bundle adjustment withdifferent feature points
    Depth images generated by different algorithms. (a) Input images; (b) depth images generated by Ref. [23]; (c) depth images generated by Ref. [24]; (d) depth images generated by proposed algorithm
    Fig. 10. Depth images generated by different algorithms. (a) Input images; (b) depth images generated by Ref. [23]; (c) depth images generated by Ref. [24]; (d) depth images generated by proposed algorithm
    AlgorithmMean standarddeviation
    Corner point295.33
    Sub-pixel corner point128.92
    Corner point after segmentation91.49
    Sub-pixel corner point after segmentation29.11
    Table 1. Mean standard deviation of focal length of different feature point beam algorithms
    AlgorithmRef.[23]Ref. [24]Proposed
    Rel0.420.350.34
    Sq Rel38.2225.3523.02
    RMS66.8763.5060.58
    SSIM0.850.730.80
    Table 2. Objective evaluation index of depth images
    Hong Yang, Aijun Xu. Tree Depth Image Generation Algorithm Based on Short Video Images[J]. Laser & Optoelectronics Progress, 2020, 57(16): 161011
    Download Citation