• Laser & Optoelectronics Progress
  • Vol. 59, Issue 14, 1415026 (2022)
Rong Jiang1,2,3, Pan Zhu1,2,3,*, Xinglin Zhou1,2,3, and Lu Liu1,2,3
Author Affiliations
  • 1School of Machinery and Automation, Wuhan University of Science and Technology, Wuhan 430081, Hubei , China
  • 2Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, Hubei , China
  • 3Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan 430081, Hubei , China
  • show less
    DOI: 10.3788/LOP202259.1415026 Cite this Article Set citation alerts
    Rong Jiang, Pan Zhu, Xinglin Zhou, Lu Liu. Three-Dimensional Pavement Texture Information Acquisition Based on Binocular Vision Algorithm[J]. Laser & Optoelectronics Progress, 2022, 59(14): 1415026 Copy Citation Text show less
    Image pyramid model and DOG pyramid generation process
    Fig. 1. Image pyramid model and DOG pyramid generation process
    Binocular vision measurement experimental platform
    Fig. 2. Binocular vision measurement experimental platform
    Working flow chart of binocular vision measurement system
    Fig. 3. Working flow chart of binocular vision measurement system
    Checkerboard calibration images
    Fig. 4. Checkerboard calibration images
    Image preprocessing of asphalt sample
    Fig. 5. Image preprocessing of asphalt sample
    Sample and experimental site. (a) Sample diagram; (b) binocular measurement; (c) laser measurement
    Fig. 6. Sample and experimental site. (a) Sample diagram; (b) binocular measurement; (c) laser measurement
    Disparity maps obtained by different cost calculation methods. (a) Census; (b) Census+color information; (c) color information+gradient information
    Fig. 7. Disparity maps obtained by different cost calculation methods. (a) Census; (b) Census+color information; (c) color information+gradient information
    Disparity maps obtained by different cost aggregation methods. (a) Guided filtering; (b) segmentation tree; (c) box filtering
    Fig. 8. Disparity maps obtained by different cost aggregation methods. (a) Guided filtering; (b) segmentation tree; (c) box filtering
    Parallax graphs obtained by the different algorithms. (a) SGBM; (b) algorithm before introducing cross scale aggregation model; (c) proposed algorithm
    Fig. 9. Parallax graphs obtained by the different algorithms. (a) SGBM; (b) algorithm before introducing cross scale aggregation model; (c) proposed algorithm
    Three dimensional model of laser measurement and the proposed algorithm measurement. (a) Laser measurement; (b) proposed algorithm measurement
    Fig. 10. Three dimensional model of laser measurement and the proposed algorithm measurement. (a) Laser measurement; (b) proposed algorithm measurement
    EquipmentParameterContent
    CameraCamera modelMV-VDM200SM/SC
    Imaging resolution /(pixel×pixel)1600×1200
    Pixel size /(μm×μm)4.4×4.4
    Sensor typeCCD
    Frame rate /(frame·s-120
    Exposure methodFrame exposure
    Power /W1.25
    Table 1. Detailed equipment parameters of the binocular vision measurement platform
    SampleMeasurement methodMTD /mmRelative error /%
    13D laser scanner0.67883.15
    Proposed algorithm0.6574
    23D laser scanner1.2032.99
    Proposed algorithm1.167
    Table 2. MTD of asphalt pavement samples
    Rong Jiang, Pan Zhu, Xinglin Zhou, Lu Liu. Three-Dimensional Pavement Texture Information Acquisition Based on Binocular Vision Algorithm[J]. Laser & Optoelectronics Progress, 2022, 59(14): 1415026
    Download Citation