• Laser & Optoelectronics Progress
  • Vol. 60, Issue 12, 1215004 (2023)
Shuhua Zhou, Sixiang Xu*, Chenchen Dong, and Hao Zhang
Author Affiliations
  • College of Mechanical Engineering, Anhui University of Technology, Maanshan243032, Anhui, China
  • show less
    DOI: 10.3788/LOP221272 Cite this Article Set citation alerts
    Shuhua Zhou, Sixiang Xu, Chenchen Dong, Hao Zhang. Algorithm for Binocular Vision Measurements Based on Local Information Entropy and Gradient Drift[J]. Laser & Optoelectronics Progress, 2023, 60(12): 1215004 Copy Citation Text show less
    Flow chart of continuous casting slab ranging
    Fig. 1. Flow chart of continuous casting slab ranging
    Comparison diagrams of entropy value of continuous casting slab model. (a) Continuous casting slab model diagram;(b) continuous casting slab model entropy diagram
    Fig. 2. Comparison diagrams of entropy value of continuous casting slab model. (a) Continuous casting slab model diagram;(b) continuous casting slab model entropy diagram
    Schematic diagram of improved rotation invariant LBP
    Fig. 3. Schematic diagram of improved rotation invariant LBP
    Flow chart of gradient drift
    Fig. 4. Flow chart of gradient drift
    Schematic diagrams of gradient drift. (a) Schematic diagram of single drift; (b) schematic diagram of n drifts
    Fig. 5. Schematic diagrams of gradient drift. (a) Schematic diagram of single drift; (b) schematic diagram of n drifts
    Before stereo correction (the top) and after stereo correction (the bottom)
    Fig. 6. Before stereo correction (the top) and after stereo correction (the bottom)
    Detection results for different information entropy thresholds
    Fig. 7. Detection results for different information entropy thresholds
    Comparison results of feature detection. (a) Detection results of traditional SIFT algorithm; (b) detection results of traditional SURF algorithm; (c) detection results of traditional ORB algorithm; (d) detection results of proposed algorithm
    Fig. 8. Comparison results of feature detection. (a) Detection results of traditional SIFT algorithm; (b) detection results of traditional SURF algorithm; (c) detection results of traditional ORB algorithm; (d) detection results of proposed algorithm
    Matching effect diagrams. (a) Traditional ORB algorithm rotated 0°; (b) proposed algorithm rotated 0°; (c) traditional ORB algorithm rotated 45°; (d) proposed algorithm rotated 45°; (e) traditional ORB algorithm rotated 180°; (f) proposed algorithm rotated 180°
    Fig. 9. Matching effect diagrams. (a) Traditional ORB algorithm rotated 0°; (b) proposed algorithm rotated 0°; (c) traditional ORB algorithm rotated 45°; (d) proposed algorithm rotated 45°; (e) traditional ORB algorithm rotated 180°; (f) proposed algorithm rotated 180°
    Comparison results of matching accuracy and matching time. (a) Comparison results of matching accuracy; (b) comparison results of matching time
    Fig. 10. Comparison results of matching accuracy and matching time. (a) Comparison results of matching accuracy; (b) comparison results of matching time
    Matching points filtering
    Fig. 11. Matching points filtering
    Parameters in the left cameraParameters in the right camera
    2201.7-2.7064902.151002199620.98820012201.7-1.3224810.714202199539.9540001
    Table 1. Internal parameters in binocular camera
    Rotation matrix RTranslation matrix T
    0.99880.0024-0.0480-0.00291.0000-0.00920.04800.00930.9988-101.9358-0.2669-2.7488
    Table 2. External parameters in binocular camera
    ParameterSIFT algorithmSURF algorithmORB algorithmProposed algorithm
    Number of features440359309176
    Time /ms178171550.56181.821122.814
    Table 3. Comparison results of feature detection data
    No.The left image coordinates before gradient drift /pixelThe left image coordinates after gradient drift /pixelDrift times
    A(691.411,578.248)(691.411,578.248)0
    B(615.847,607.103)(615.995,605.662)2
    C(602.562,752.617)(603.996,753.417)4
    D(1288.445,959.549)(1287.945,957.812)3
    A(462.151,577.643)(462.225,578.344)3
    B(373.226,604.886)(373.226,605.291)2
    C(363.613,751.803)(363.608,753.103)2
    D(1010.215,958.468)(1009.224,957.468)1
    Table 4. Pixel coordinate update results from gradient drift (1)
    No.Three-dimensional coordinates before gradient driftThree-dimensional coordinates after gradient drift
    A(71.4026,0.4204,-978.9412)(71.4257,0.5764,-979.2572)
    B(99.2183,12.1819,-925.0314)(99.0957,11.9569,-924.4675)
    C(-106.4104,74.7447,-939.2467)(-105.1653,74.7425,-933.6242)
    D(159.9014,139.9574,-806.6422)(159.4369,139.2103,-805.2212)
    Table 5. Three-dimensional coordinate update results from gradient drift
    SideMeasurement results /mmActual size /mmAbsolute error /mmRelative error /%
    AB62.426630.573-0.910
    BC63.739630.7391.173
    CD301.0943001.0940.365
    Table 6. Measurement results of continuous casting slab model
    No.Ranging length /mmActual length /mmAbsolute error /mmRelative error /%
    1305.6803005.6801.893
    2294.2213005.779-1.926
    3305.7803005.7801.927
    4294.3193005.681-1.894
    5305.8403005.8401.947
    Mean301.1683005.7521.917
    Table 7. Measurement results of traditional SIFT algorithm
    No.Ranging length /mmActual length /mmAbsolute error /mmRelative error /%
    1295.3453004.655-1.552
    2304.5633004.5631.521
    3304.7003004.7001.567
    4295.4353004.565-1.522
    5304.6533004.6531.551
    Mean300.9393004.6271.542
    Table 8. Measurement results of traditional ORB algorithm
    No.Ranging length /mmActual length /mmAbsolute error /mmRelative error /%
    1301.0943001.0940.365
    2301.1373001.1370.379
    3298.8873001.113-0.371
    4298.7733001.227-0.409
    5301.1583001.1580.386
    Mean300.2103001.1460.382
    Table 9. Measurement results of proposed algorithm
    Shuhua Zhou, Sixiang Xu, Chenchen Dong, Hao Zhang. Algorithm for Binocular Vision Measurements Based on Local Information Entropy and Gradient Drift[J]. Laser & Optoelectronics Progress, 2023, 60(12): 1215004
    Download Citation