• Acta Optica Sinica
  • Vol. 40, Issue 21, 2115002 (2020)
Dian Fei, Jianlin Chen, Dongsheng Liu, and Zhijiang Zhang*
Author Affiliations
  • Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University, Shanghai 200444, China
  • show less
    DOI: 10.3788/AOS202040.2115002 Cite this Article Set citation alerts
    Dian Fei, Jianlin Chen, Dongsheng Liu, Zhijiang Zhang. Depth Camera-Based Location and Restoration of Special Surface[J]. Acta Optica Sinica, 2020, 40(21): 2115002 Copy Citation Text show less
    Diagram of system
    Fig. 1. Diagram of system
    Depth image preprocessing. (a) Raw depth image; (b) shadow noise area; (c) ROI segmentation; (d) reliability mask
    Fig. 2. Depth image preprocessing. (a) Raw depth image; (b) shadow noise area; (c) ROI segmentation; (d) reliability mask
    Depth histogram
    Fig. 3. Depth histogram
    Weight setting near depth edge. (a) σ0 neighborhood range; (b) ωm function curve
    Fig. 4. Weight setting near depth edge. (a) σ0 neighborhood range; (b) ωm function curve
    TSDF variation ηTS. (a) Color image; (b)-(d) ηTSγlη-TS, low pass filter parameter γl=0.6, 0.7, 0.8; (e)-(h) ηTS>γh<math id="Mml17" xmlns:mml="h
    Fig. 5. TSDF variation ηTS. (a) Color image; (b)-(d) ηTS<γlη-TS, low pass filter parameter γl=0.6, 0.7, 0.8; (e)-(h) ηTS>γhDownload full size
    Reference frame FIFO queue
    Fig. 6. Reference frame FIFO queue
    Model reparation experiment. (a) Model before reparation; (b) model after reparation; (c) experimental environment and setting; (d) peculiar object; (e) model detail before reparation; (f) model detail after reparation
    Fig. 7. Model reparation experiment. (a) Model before reparation; (b) model after reparation; (c) experimental environment and setting; (d) peculiar object; (e) model detail before reparation; (f) model detail after reparation
    Models corresponding to different pose results. (a) Experimental setting; (b) KinectFusion; (c) SDF-tracker; (d) proposed method
    Fig. 8. Models corresponding to different pose results. (a) Experimental setting; (b) KinectFusion; (c) SDF-tracker; (d) proposed method
    Comparison of reconstruction results 1. (a) Experimental environment and setting; (b)camera pose; (c) result obtained by algorithm Ⅰ; (d) result obtained by proposed method
    Fig. 9. Comparison of reconstruction results 1. (a) Experimental environment and setting; (b)camera pose; (c) result obtained by algorithm Ⅰ; (d) result obtained by proposed method
    Comparison of reconstruction results 2. (a) Experimental environment and setting; (b)camera pose; (c)(d) result obtained by algorithm Ⅰ; (e)(f) result obtained by proposed method
    Fig. 10. Comparison of reconstruction results 2. (a) Experimental environment and setting; (b)camera pose; (c)(d) result obtained by algorithm Ⅰ; (e)(f) result obtained by proposed method
    MethodAverage pose errorafter 100 framesAverage pose errorafter 300 framesAverage pose errorafter 600 frames
    KinectFusion32.838.262.6
    SDF-tracker26.127.533.8
    Proposed method25.727.029.7
    Table 1. Error analysis of pose tracking in experiment Ⅰmm
    MethodAverage pose errorafter 100 framesAverage pose errorafter 300 framesAverage pose errorafter 600 frames
    KinectFusion51.0100.2811.2
    SDF-tracker28.933.438.8
    Proposed method30.533.233.7
    Table 2. Error analysis of pose tracking in experiment Ⅱmm
    Dian Fei, Jianlin Chen, Dongsheng Liu, Zhijiang Zhang. Depth Camera-Based Location and Restoration of Special Surface[J]. Acta Optica Sinica, 2020, 40(21): 2115002
    Download Citation