Turn off MathJax
Article Contents
WU Fu-pei, HUANG Geng-nan, LIU Yu-hao, YE Wei-lin, LI Sheng-ping. Stereo matching algorithm based on multi-feature SAD-Census transformation[J]. Chinese Optics. doi: 10.37188/CO.2023-0082
Citation: WU Fu-pei, HUANG Geng-nan, LIU Yu-hao, YE Wei-lin, LI Sheng-ping. Stereo matching algorithm based on multi-feature SAD-Census transformation[J].Chinese Optics.doi:10.37188/CO.2023-0082

Stereo matching algorithm based on multi-feature SAD-Census transformation

doi:10.37188/CO.2023-0082
Funds:Supported by
More Information
  • The high mismatch rate of the parallax discontinuity region and the repeated texture region has been a major issue affecting the measurement accuracy of binocular stereo matching. For these reasons, this paper proposes a stereo matching algorithm that utilize multi-feature fusion. Firstly, the weight of neighboring pixels is given using Gaussian weighting method, which optimizes the calculation accuracy of the Sum of Absolute Differences (SAD) algorithm. Based on the Census transformation, the binary chain code technique has been enhanced to fuse the average gray value of neighborhood pixels with the average gray value of gradient image, and then the judgment basis of the left and right image corresponding points is established, and the coding length is optimized. Secondly, an aggregation technique has been developed that combines the cross method and the improved guide filter to redistribute disparity values with the aim of minimizing error. Finally, the initial disparity is obtained by the Winner Take All (WTA) algorithm, and the final disparity results are obtained by the left-right consistency detection method, sub-pixel method, and then a stereo matching algorithm based on the multi-feature SAD Census transform is established. The experimental results show that the average error matching rate of the proposed algorithm is 4.18%, the average error of the 200−900 mm distance is less than 2%, and the maximum error of the actual 3D data measurement is 1.5%, all using the test of the Middlebury dataset. The experimental results verify the effectiveness of the proposed algorithm.

  • loading
  • [1]
    陈仁虹, 梁晋, 叶美图, 等. 柔性复合薄膜成形极限曲线的视觉测定方法[J]. 中国光学,2022,15(1):22-33. doi:10.37188/CO.2021-0101

    CHEN R H, LIANG J, YE M T, et al. Visual method for measuring forming limit curve of pliable composite film[J]. Chinese Optics, 2022, 15(1): 22-33. (in Chinese) doi:10.37188/CO.2021-0101
    [2]
    任晓奎, 关钧渤, 殷新勇, 等. 基于改进局部一致性约束的立体匹配算法[J]. 液晶与显示,2023,38(4):543-553. doi:10.37188/CJLCD.2022-0226

    REN X K, GUAN J B, YIN X Y, et al. Stereo matching algorithm based on improved local consistency constraint[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(4): 543-553. (in Chinese) doi:10.37188/CJLCD.2022-0226
    [3]
    张强, 刘婷婷, 李海滨, 等. 基于最佳搜索域的水下图像区域匹配算法研究[J]. 光学学报,2014,34(6):0615001. doi:10.3788/AOS201434.0615001

    ZHANG Q, LIU T T, LI H B, et al. Research on region matching for underwater images based on optimum searching area[J]. Acta Optica Sinica, 2014, 34(6): 0615001. (in Chinese) doi:10.3788/AOS201434.0615001
    [4]
    LEE J, JUN D, EEM C, et al. Improved census transform for noise robust stereo matching[J]. Optical Engineering, 2016, 55(6): 063107. doi:10.1117/1.OE.55.6.063107
    [5]
    彭新俊, 韩军, 汤踊, 等. 基于改进Census变换和异常值剔除的抗噪立体匹配算法[J]. 光学学报,2017,37(11):1115004. doi:10.3788/AOS201737.1115004

    PENG X J, HAN J, TANG Y, et al. Anti-noise stereo matching algorithm based on improved census transform and outlier elimination[J]. Acta Optica Sinica, 2017, 37(11): 1115004. (in Chinese) doi:10.3788/AOS201737.1115004
    [6]
    刘建国, 俞力, 柳思健, 等. 基于改进Census变换和多尺度空间的立体匹配算法[J]. 华南理工大学学报(自然科学版),2017,45(12):43-49.

    LIU J G, YU L, LIU S J, et al. Stereo matching algorithm based on improved census transform and multi-scale space[J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45(12): 43-49. (in Chinese)
    [7]
    杨春雨, 顾振, 张鑫, 等. 基于深度学习的带式输送机煤流量双目视觉测量[J]. 仪器仪表学报,2021,42(8):164-174.

    YANG CH Y, GU ZH, ZHANG X, et al. Binocular vision measurement of coal flow of belt conveyors based on deep learning[J]. Chinese Journal of Scientific Instrument, 2021, 42(8): 164-174. (in Chinese)
    [8]
    HOSNI A, BLEYER M, GELAUTZ M. Secrets of adaptive support weight techniques for local stereo matching[J]. Computer Vision and Image Understanding, 2013, 117(6): 620-632. doi:10.1016/j.cviu.2013.01.007
    [9]
    孔令寅, 朱江平, 应三丛. 基于引导图像和自适应支持域的立体匹配[J]. 光学学报,2020,40(9):0915001. doi:10.3788/AOS202040.0915001

    KONG L Y, ZHU J P, YING S C. Stereo matching based on guidance image and adaptive support region[J]. Acta Optica Sinica, 2020, 40(9): 0915001. (in Chinese) doi:10.3788/AOS202040.0915001
    [10]
    CHANG N Y C, TSAI T H, HSU B H, et al. Algorithm and architecture of disparity estimation with mini-census adaptive support weight[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010, 20(6): 792-805. doi:10.1109/TCSVT.2010.2045814
    [11]
    王森, 危辉, 孟令江. 基于控制点和RGB向量差联合梯度Census变换的立体匹配算法[J]. 模式识别与人工智能,2022,35(1):37-50.

    WANG S, WEI H, MENG L J. Stereo matching algorithm based on control points, RGB vector difference and gradient census transform[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(1): 37-50. (in Chinese)
    [12]
    ZHANG K, LU J B, LAFRUIT G. Cross-based local stereo matching using orthogonal integral images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2009, 19(7): 1073-1079. doi:10.1109/TCSVT.2009.2020478
    [13]
    WANG W Q, YAN J, XU N Y, et al. Real-time high-quality stereo vision system in FPGA[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2015, 25(10): 1696-1708. doi:10.1109/TCSVT.2015.2397196
    [14]
    CHENG F Y, ZHANG H, SUN M G, et al. Cross-trees, edge and superpixel priors-based cost aggregation for stereo matching[J]. Pattern Recognition, 2015, 48(7): 2269-2278. doi:10.1016/j.patcog.2015.01.002
    [15]
    洪梓嘉, 李彦明, 林洪振, 等. 基于双目视觉的种植前期农田边界距离检测方法[J]. 农业机械学报,2022,53(5):27-33,56.

    HONG Z J, LI Y M, LIN H ZH, et al. Field boundary distance detection method in early stage of planting based on binocular vision[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(5): 27-33,56. (in Chinese)
    [16]
    ZHAN Y L, GU Y Z, ZHANG X L, et al. Stereo matching based on efficient image-guided cost aggregation[J]. IEICE Transactions on Information and Systems, 2016, E99.D(3): 781-784. doi:10.1587/transinf.2015EDL8223
    [17]
    YAO M, OUYANG W B, XU B G. Hybrid cost aggregation for dense stereo matching[J]. Multimedia Tools and Applications, 2020, 79(31): 23189-23202.
    [18]
    YANG Q X. Stereo matching using tree filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(4): 834-846. doi:10.1109/TPAMI.2014.2353642
    [19]
    HIRSCHMÜLLER H. Accurate and efficient stereo processing by semi-global matching and mutual information[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, 2005: 807-814.
    [20]
    张建业, 朴燕. 基于改进稳态匹配概率的立体匹配算法研究[J]. 液晶与显示,2018,33(4):357-364. doi:10.3788/YJYXS20183304.0357

    ZHANG J Y, PIAO Y. Stereo matching algorithm based on improved steady-state matching probability[J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(4): 357-364. (in Chinese) doi:10.3788/YJYXS20183304.0357
    [21]
    LI ZH G, ZHENG J H, ZHU Z J, et al. Weighted guided image filtering[J]. IEEE Transactions on Image Processing, 2015, 24(1): 120-129. doi:10.1109/TIP.2014.2371234
    [22]
    HUMENBERGER M, ZINNER C, WEBER M, et al. A fast stereo matching algorithm suitable for embedded real-time systems[J]. Computer Vision and Image Understanding, 2010, 114(11): 1180-1202. doi:10.1016/j.cviu.2010.03.012
    [23]
    刘杰, 张建勋, 代煜, 等. 基于跨尺度引导图像滤波的稠密立体匹配[J]. 光学学报,2018,38(1):0115004. doi:10.3788/AOS201838.0115004

    LIU J, ZHANG J X, DAI Y, et al. Dense stereo matching based on cross-scale guided image filtering[J]. Acta Optica Sinica, 2018, 38(1): 0115004. (in Chinese) doi:10.3788/AOS201838.0115004
    [24]
    KOLMOGOROV V, ZABIH R. Computing visual correspondence with occlusions using graph cuts[C]. IEEE International Conference on Computer Vision, IEEE, 2001: 508-515.
    [25]
    DE-MAEZTU L, VILLANUEVA A, CABEZA R. Stereo matching using gradient similarity and locally adaptive support-weight[J]. Pattern Recognition Letters, 2011, 32(13): 1643-1651. doi:10.1016/j.patrec.2011.06.027
    [26]
    任久斌. 基于双目立体视觉的三维重建技术研究[D]. 成都: 西南交通大学, 2020.

    REN J B. Research on 3D reconstruction technology based on binocular stereo vision[D]. Chengdu: Southwest Jiaotong University, 2020. (in Chinese)
    [27]
    符强, 孔健明, 纪元法, 等. 基于双目视觉的无人机实时测距算法[J]. 电光与控制,2023,30(4):94-99.

    FU Q, KONG J M, JI Y F, et al. A method of UAV real-time ranging based on binocular vision[J]. Electronics Optics & Control, 2023, 30(4): 94-99. (in Chinese)
    [28]
    仲伟波, 姚旭洋, 冯友兵, 等. 双目区域视差快速计算及测距算法[J]. 中国图象图形学报,2019,24(9):1537-1545.

    ZHONG W B, YAO X Y, FENG Y B, et al. Rapid calculation and ranging algorithm based on binocular region parallax[J]. Journal of Image and Graphics, 2019, 24(9): 1537-1545. (in Chinese)
    [29]
    肖纯, 林嘉欣, 王玮. 基于双目测距的晶英石板自动打磨系统研究[J]. 武汉理工大学学报,2018,40(3):78-83.

    XIAO CH, LIN J X, WANG W. Research on automatic jing ying stone grinding system based on binocular distance measurement[J]. Journal of Wuhan University of Technology, 2018, 40(3): 78-83. (in Chinese)
    [30]
    HUANG L, WU G P, LIU J Y, et al. Obstacle distance measurement based on binocular vision for high-voltage transmission lines using a cable inspection robot[J]. Science Progress, 2020, 103(3): 003685042093691. (查阅网上资料, 页码信息不确定, 请确认).

    HUANG L, WU G P, LIU J Y, et al. . Obstacle distance measurement based on binocular vision for high-voltage transmission lines using a cable inspection robot[J]. Science Progress, 2020, 103(3): 003685042093691. (查阅网上资料, 页码信息不确定, 请确认).
  • 加载中

Catalog

    通讯作者:陈斌, bchen63@163.com
    • 1.

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(11)/Tables(5)

    Article views(35) PDF downloads(28) Cited by()
    Proportional views

    /

    Return
    Return
      Baidu
      map