• Acta Optica Sinica
  • Vol. 38, Issue 1, 0115004 (2018)
Jie Liu*, Jianxun Zhang, Yu Dai, and He Su
Author Affiliations
  • Institute of Robotics & Automatic Information System, Nankai University Tianjin 300071, China
  • show less
    DOI: 10.3788/AOS201838.0115004 Cite this Article Set citation alerts
    Jie Liu, Jianxun Zhang, Yu Dai, He Su. Dense Stereo Matching Based on Cross-Scale Guided Image Filtering[J]. Acta Optica Sinica, 2018, 38(1): 0115004 Copy Citation Text show less
    (a) Support weights of effective pixels in support regions; (b) corresponding adaptive support regions
    Fig. 1. (a) Support weights of effective pixels in support regions; (b) corresponding adaptive support regions
    Initial disparity maps with different sizes of filter kernels. (a) l=r˙cmin; (b) l=r˙min; (c) l=r˙max; (d) initial disparity map with regularization term
    Fig. 2. Initial disparity maps with different sizes of filter kernels. (a) l=r˙cmin; (b) l=r˙min; (c) l=r˙max; (d) initial disparity map with regularization term
    Flowchart of proposed algorithm
    Fig. 3. Flowchart of proposed algorithm
    Disparity maps of stereo matching algorithms based on image filtering. (a) Original color images; (b) real disparity maps; (c) disparity maps obtained by guided filtering cost aggregation; (d) disparity maps obtained by multiscale guided filtering cost aggregation; (e) disparity maps obtained by proposed algorithm
    Fig. 4. Disparity maps of stereo matching algorithms based on image filtering. (a) Original color images; (b) real disparity maps; (c) disparity maps obtained by guided filtering cost aggregation; (d) disparity maps obtained by multiscale guided filtering cost aggregation; (e) disparity maps obtained by proposed algorithm
    Comparison of running time and matching accuracy of several stereo matching algorithms based on guided image filtering
    Fig. 5. Comparison of running time and matching accuracy of several stereo matching algorithms based on guided image filtering
    AlgorithmTsukubaVenusTeddyConesAvgPBM
    n-occAlldiscn-occAlldiscn-occAlldiscn-occAlldisc
    Proposed2.382.858.41.131.989.267.0514.916.83.3211.07.997.09
    BF[7]2.933.379.401.892.679.439.3917.219.65.2913.712.38.94
    GF[10]2.623.388.161.722.8113.28.1516.517.53.3412.28.698.20
    S-GF[12]2.302.948.121.091.999.677.0415.116.72.9911.48.177.29
    GlobalGCP*200.872.544.690.460.532.226.4411.516.23.599.498.95.60
    VarCross*211.992.656.770.620.963.209.7515.118.26.2812.712.97.60
    Table 1. Percentage of mismatching pixels of different algorithms
    Jie Liu, Jianxun Zhang, Yu Dai, He Su. Dense Stereo Matching Based on Cross-Scale Guided Image Filtering[J]. Acta Optica Sinica, 2018, 38(1): 0115004
    Download Citation