• Laser & Optoelectronics Progress
  • Vol. 59, Issue 8, 0810013 (2022)
Chaoqun Song1、2, Sixiang Xu1、2、*, Yu Yang1、2, and Mengqi Hua1、2
Author Affiliations
  • 1Anhui Province Key Laboratory of Special Heavy Load Robot, Anhui University of Technology, Maanshan, Anhui 243032, China
  • 2School of Mechanical Engineering, Anhui University of Technology, Maanshan, Anhui 243032, China
  • show less
    DOI: 10.3788/LOP202259.0810013 Cite this Article Set citation alerts
    Chaoqun Song, Sixiang Xu, Yu Yang, Mengqi Hua. Binocular Vision Measurement Method Using Improved FAST and BRIEF[J]. Laser & Optoelectronics Progress, 2022, 59(8): 0810013 Copy Citation Text show less
    Diagram of binocular stereo imaging principle
    Fig. 1. Diagram of binocular stereo imaging principle
    Flow chart of slab size measurement
    Fig. 2. Flow chart of slab size measurement
    Center of the circle in FAST algorithm and its circumference with 16 pixels
    Fig. 3. Center of the circle in FAST algorithm and its circumference with 16 pixels
    Corner detection template
    Fig. 4. Corner detection template
    Comparison of the slab model before and after correction. (a) Before correction; (b) after correction
    Fig. 5. Comparison of the slab model before and after correction. (a) Before correction; (b) after correction
    Comparison of corner detection of the slab model. (a) Traditional FAST; (b) proposed improved FAST
    Fig. 6. Comparison of corner detection of the slab model. (a) Traditional FAST; (b) proposed improved FAST
    Comparison of corner detection of Blox picture. (a) Traditional FAST; (b) proposed improved FAST
    Fig. 7. Comparison of corner detection of Blox picture. (a) Traditional FAST; (b) proposed improved FAST
    Matching diagram
    Fig. 8. Matching diagram
    Final matching point pairs
    Fig. 9. Final matching point pairs
    Calculating sub-pixel corner points
    Fig. 10. Calculating sub-pixel corner points
    Feature point matching. (a) SIFT algorithm; (b) traditional FSAT+BRIEF; (c) algorithm in Ref.[10]; (d) proposed algorithm
    Fig. 11. Feature point matching. (a) SIFT algorithm; (b) traditional FSAT+BRIEF; (c) algorithm in Ref.[10]; (d) proposed algorithm
    Parameter in left cameraParameter in right camera
    2200.5-1.3997737.841602205.7568.32200012223.3-2.3103752.202228.9620.9001
    Table 1. Calibration result of internal parameters in binocular system
    Rotation matrix RTranslation matrix T
    0.99990.00500.0156-0.00501.00000.0029-0.0155-0.00290.9999-100.93930.780411.5155
    Table 2. Calibration result of external parameters in binocular system
    ParameterDetection targetTraditional FAST algorithmProposed FAST algorithm
    Number of feature pointsSlab model501161
    Blox431294
    Time /sSlab model0.1480.326
    Blox0.2150.374
    Table 3. Comparison of detection results of two FAST algorithms
    PointLeft image pixel coordinate /pixelRight image pixel coordinate /pixelCoordinate in the world coordinate system /mm
    A(723.77, 717.487)(571.616, 717.918)(-79.7535, 100.9622, 1459.6821)
    B(725.41, 568.935)(573.926, 568.744)(-79.0136, 2.2250, 1466.1381)
    C(805.564, 561.832)(659.936, 562.203)(-26.6387, -2.4136, 1525.0945)
    D(1124.86, 588.755)(961.164, 588.999)(173.1698, 14.4136, 1356.7617)
    Table 4. Matching point coordinates
    SideMeasured size /mm

    Actual

    size /mm

    Relative error /%
    AB98.95081001.05
    BC78.9968801.25
    CD261.80632630.45
    Table 5. Size measurement results of the slab model
    Matching algorithmNumber of coarse matching point pairsNumber of correct matching point pairsCorrect rate /%Total time /s
    SIFT algorithm683044.129.956
    Traditional FAST+BRIEF1806837.781.108
    Algorithm in Ref.[10844654.761.400
    Proposed algorithm1279675.592.035
    Table 6. Comparison results of the four algorithms
    AlgorithmDistance measuring length /mmTrue length /mmRunning time /sRelative error /%
    Traditional FAST+BRIEF259.48352631.4721.34
    Algorithm in Ref.[10260.52562631.6880.94
    Proposed algorithm261.80632631.8590.45
    Table 7. Slab measurement accuracy analysis
    Chaoqun Song, Sixiang Xu, Yu Yang, Mengqi Hua. Binocular Vision Measurement Method Using Improved FAST and BRIEF[J]. Laser & Optoelectronics Progress, 2022, 59(8): 0810013
    Download Citation