Laser & Optoelectronics Progress, Volume. 56, Issue 10, 101502(2019)

Stereo-Matching Algorithm Using Weighted Guided Image Filtering Based on Laplacian of Gaussian Operator

Bo Zhou1,2、*, Ling Qin1,2、**, and Wei Gong1,2、***
Author Affiliations
  • 1 Hubei Key Laboratory of Advanced Technology for Automotive Components (Wuhan University of Technology), Wuhan, Hubei 430070, China
  • 2 Hubei Collaborative Innovation Center for Automotive Components Technology, Wuhan, Hubei 430070, China
  • show less
    Figures & Tables(8)
    Comparison of different matching costs. (a) Single channel AD; (b) mean AD; (c) weighted AD
    Comparison of disparity maps before and after improvement by guided image filtering. (a) Before improvement; (b) after improvement
    Comparison of mismatch rates before and after improvement by guided image filtering
    Disparity selection and refinement process. (a) Matching result of left image; (b) test result of left-right consistency; (c) result of first interpolation; (d) result of second interpolation
    Comparison of details for two interpolations. (a) Result of first interpolation; (b) result of second interpolation
    Result of proposed algorithm. (a) Original left images; (b) ground truth; (c) disparity maps obtained by proposed algorithm; (d) mismatching points gained by proposed algorithm
    • Table 1. Mismatching rates of different stereo-matching algorithms in non-occluded regions and all regions of four groups of test image sets%

      View table

      Table 1. Mismatching rates of different stereo-matching algorithms in non-occluded regions and all regions of four groups of test image sets%

      AlgorithmTsukubaVenusTeddyConesAverage
      NonoccAllNonoccAllNonoccAllNonoccAll
      GC-occ1.192.011.642.1911.2017.405.3612.406.67
      RTCensus5.086.251.582.427.9613.804.109.546.34
      Fast Aggreg1.162.114.034.759.0415.205.3712.606.78
      Semi Glob3.263.961.001.576.0212.203.069.755.10
      Adapt Weight1.381.850.711.197.8813.303.979.795.01
      RTAdapt Weight1.451.990.400.817.6513.303.489.344.80
      Proposed algorithm1.812.650.270.516.7510.152.789.624.32
    • Table 2. Mismatching rates of different stereo-matching algorithms in non-occluded regions of other 27 groups of test image sets%

      View table

      Table 2. Mismatching rates of different stereo-matching algorithms in non-occluded regions of other 27 groups of test image sets%

      StereoDatasetAdaptWeightMSTFast CostProposedalgorithm
      Aloe6.5026.6137.0645.161
      Art12.88313.74412.0328.961
      Baby15.4537.6543.1613.602
      Baby213.64314.1243.9714.252
      Baby38.7639.5344.7116.092
      Books12.65312.97410.2128.681
      Bowling116.87319.1446.21111.652
      Bowling210.43312.6348.1827.661
      Cloth11.2531.1821.8840.891
      Cloth25.5645.4034.2023.071
      Cloth33.8143.2032.7921.921
      Cloth43.2142.5332.2521.621
      Dolls6.4327.8647.1234.511
      Flowerpots15.44317.2749.63113.612
      Lampshade112.36411.29212.12310.801
      Lampshade217.44314.20212.48122.594
      Laundry16.89219.39320.64413.531
      Midd136.47218.96136.95340.364
      Midd235.56320.21134.02238.084
      Moebius13.26411.33310.6429.741
      Monopoly15.43116.85219.74324.064
      Plastic32.44330.30227.06141.094
      Reindeer11.73311.9647.8424.941
      Rocks15.4344.1433.9722.241
      Rocks25.0243.3332.6721.391
      Wood18.99311.1744.9323.981
      Wood26.1544.2032.7120.481
      Average12.59411.52310.34110.922
    Tools

    Get Citation

    Copy Citation Text

    Bo Zhou, Ling Qin, Wei Gong. Stereo-Matching Algorithm Using Weighted Guided Image Filtering Based on Laplacian of Gaussian Operator[J]. Laser & Optoelectronics Progress, 2019, 56(10): 101502

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Nov. 27, 2018

    Accepted: Dec. 14, 2018

    Published Online: Jul. 4, 2019

    The Author Email: Zhou Bo (zhoubo180@foxmail.com), Qin Ling (qinling@whut.edu.cn), Gong Wei (gongwei_whut@163.com)

    DOI:10.3788/LOP56.101502

    Topics