摘要

立体匹配算法在图像弱纹理区和重复纹理区存在匹配困难、误差大的问题,为此提出一种基于改进代价计算和视差候选策略的立体匹配算法。首先结合改进的Census变换和自适应加权融合的双向梯度信息来计算初始匹配代价,提高代价计算的可靠性。其中:为传统Census变换增加内圈编码,提高邻域信息利用率,同时降低噪声的影响;利用自适应权重函数融合横向和纵向梯度代价,降低物体边缘区域的误匹配率。其次,采用自适应十字交叉窗口进行代价聚合,并通过建立候选视差集和引入邻域视差信息的方法来获取初始视差。最后通过两轮插值策略优化视差。实验结果表明,所提算法能够提高弱纹理区和重复纹理区的匹配效果,在Middlebury中4幅标准立体图像对的平均误匹配率为5.33%。

Abstract

Matching difficulty and the occurrence of large errors in the weak and repeated texture areas of an image are the problems associated with the stereo matching algorithm. To solve these problems, this paper proposes a stereo matching algorithm based on improved cost calculation and a disparity candidate strategy. First, the improved Census transform and adaptive weighted bidirectional gradient information are combined to estimate the initial matching cost, improving the reliability of cost calculation. Here, inner circle coding is added to the traditional Census transform for improving the utilization of neighborhood information while reducing the impact of noise. The adaptive weight function is used to combine the horizontal and vertical gradient costs for reducing the mismatching rate of the object edge areas. Second, after cost aggregation with an adaptive cross-window, the initial disparity can be obtained by establishing candidate disparity sets and introducing neighborhood disparity information. Finally, the disparity is optimized via two-round interpolation. Experimental results demonstrate that the proposed algorithm can improve the stereo matching of the weak and repeated texture areas and that the average mismatching rate on four standard stereo image pairs in Middlebury is 5.33%.

补充资料

中图分类号：TN911.73

DOI：10.3788/LOP202158.0215001

所属栏目：机器视觉

基金项目：国家自然科学基金（61972241）、上海市科委部分地方院校能力建设项目（2005051900）

收稿日期：2020-05-21

修改稿日期：2020-07-03

网络出版日期：2021-01-01

作者单位    点击查看

联系人作者：宋巍(wsong@shou.edu.cn); 贺琪(wsong@shou.edu.cn);

【1】Wu W H, Zhu H, Yu S Y, et al. Stereo matching with fusing adaptive support weights [J]. IEEE Access. 2019, 7: 61960-61974.Wu W H, Zhu H, Yu S Y, et al. Stereo matching with fusing adaptive support weights [J]. IEEE Access. 2019, 7: 61960-61974.

【2】Scharstein D, Szeliski R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms [J]. International Journal of Computer Vision. 2002, 47(1/2/3): 7-42.

【3】Kolmogorov V, Zabih R. Computing visual correspondence with occlusionsusing graph cuts[C]∥ Proceedings of 8th IEEE International Conference on Computer Vision, July 7-14, 2001, Vancouver, BC, Canada. New York: , 2001, 508-515.

【4】Besse F, Rother C, Fitzgibbon A, et al. PMBP:PatchMatch belief propagation for correspondence field estimation [J]. International Journal of Computer Vision. 2014, 110(1): 2-13.

【5】Birchfield S, Tomasi C. Depth discontinuities by pixel-to-pixel stereo [J]. International Journal of Computer Vision. 1999, 35(3): 269-293.

【6】Scharstein D. Matching images by comparing their gradient fields[C]∥Proceedings of 12th International Conference on Pattern Recognition, October 9-13, 1994, Jerusalem, Israel. New York: , 1994, 572-575.

【7】Zabih R, Woodfill J. Non-parametric local transforms for computing visual correspondence . [C]∥ Eklundh J O. Computer Vision: ECCV''94. Berlin, Heidelberg: Springer. 1994, 801: 151-158.

【8】Chen X F, Guo Z H, Wu J L, et al. De-occlusion stereo matching algorithm based on regional prior information [J]. Laser & Optoelectronics Progress. 2019, 56(19): 191001.
陈先锋, 郭正华, 伍俊龙, 等. 基于区域先验信息的去遮挡立体匹配算法 [J]. 激光与光电子学进展. 2019, 56(19): 191001.

【9】Hirschmuller H. Stereo processing by semiglobal matching and mutual information [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008, 30(2): 328-341.Hirschmuller H. Stereo processing by semiglobal matching and mutual information [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008, 30(2): 328-341.

【10】Mei X, Sun X, Zhou M C, et al. On building an accurate stereo matching system on graphics hardware[C]∥2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), November 6-13, 2011, Barcelona, Spain. New York: , 2011, 467-474.

【11】Hosni A, Rhemann C, Bleyer M, et al. Fast cost-volume filtering for visual correspondence and beyond [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2013, 35(2): 504-511.

【12】Guo X, Wang Y J, Fu D H, et al. A weight guided filtering matching algorithm combining three measures [J]. Computer Engineering & Science. 2019, 41(6): 1044-1049.
郭鑫, 王延杰, 付东辉, 等. 三种测度融合的加权引导滤波匹配算法 [J]. 计算机工程与科学. 2019, 41(6): 1044-1049.

【13】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.
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.

【14】Wang Y F, Wu W, Yu X L, et al. A stereo matching system with the adaptive weight AD-census [J]. Advanced Engineering Sciences. 2018, 50(4): 153-160.
王云峰, 吴炜, 余小亮, 等. 基于自适应权重AD-Census变换的双目立体匹配 [J]. 工程科学与技术. 2018, 50(4): 153-160.

【15】Yan L, Wang R, Liu H, et al. Stereo matching method based on improved cost computation and adaptive guided filter [J]. Acta Optica Sinica. 2018, 38(11): 1115007.
闫利, 王芮, 刘华, 等. 基于改进代价计算和自适应引导滤波的立体匹配 [J]. 光学学报. 2018, 38(11): 1115007.

【16】Salehian B, Raie A, Fotouhi A, et al. Efficient interscanline consistency enforcing method for dynamic programming-based dense stereo matching algorithms [J]. Journal of Electronic Imaging. 2013, 22(4): 043028.

【17】Wang L, Yang R G, Gong M L, et al. Real-time stereo using approximated joint bilateral filtering and dynamic programming [J]. Journal of Real-Time Image Processing. 2014, 9(3): 447-461.Wang L, Yang R G, Gong M L, et al. Real-time stereo using approximated joint bilateral filtering and dynamic programming [J]. Journal of Real-Time Image Processing. 2014, 9(3): 447-461.

【18】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.
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.

【19】Peng J J, Bai R L. Variable weight cost aggregation algorithm for stereo matching based on horizontal tree structure [J]. Acta Optica Sinica. 2018, 38(1): 0115002.
彭建建, 白瑞林. 基于水平树结构的可变权重代价聚合立体匹配算法 [J]. 光学学报. 2018, 38(1): 0115002.

【20】Zhang K, Fang Y Q, Min D B, et al. Cross-scale cost aggregation for stereo matching[C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: , 2014, 1590-1597.

【21】Ma Q Q, Wang C F. Non-local stereo matching algorithm based on color and edge information [J]. Laser & Optoelectronics Progress. 2020, 57(10): 101020.
马晴晴, 王彩芳. 基于颜色和边缘信息的非局部立体匹配算法 [J]. 激光与光电子学进展. 2020, 57(10): 101020.

【22】Zhu S P, Yan L N. Local stereo matching algorithm with efficient matching cost and adaptive guided image filter [J]. The Visual Computer. 2017, 33(9): 1087-1102.

【23】Scharstein D, Szeliski R. High-accuracy stereo depth maps using structured light[C]∥2003 IEEE Conference on Computer Vision and Pattern Recognition, June 18-20, 2003, Madison, WI, USA. New York: , 2003, 7762284.

【24】Scharstein D, Pal C. Learning conditional random fields for stereo[C]∥IEEE Conference on Computer Vision and Pattern Recognition, June 17-22, 2007, Minneapolis, MN, USA. New York: , 2007, 9738080.

【25】Mattoccia S, Tombari F, Stefano L D. Stereo vision enabling precise border localization within a scanline optimization framework . [C]∥ Proceedings of Asian Conference on Computer Vision, Berlin/Heidelberg: Springer-Verlag. 2007, 517-527.

【26】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.

【27】Zhu S P, Li Z. A stereo matching algorithm using improved gradient and adaptive window [J]. Acta Optica Sinica. 2015, 35(1): 0110003.
祝世平, 李政. 基于改进梯度和自适应窗口的立体匹配算法 [J]. 光学学报. 2015, 35(1): 0110003.

引用该论文

Song Wei,Wei Xinyu,Zhang Minghua,He Qi. Stereo Matching Based on Improved Cost Calculation and a Disparity Candidate Strategy[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0215001

宋巍,魏新宇,张明华,贺琪. 基于改进代价计算和视差候选策略的立体匹配[J]. 激光与光电子学进展, 2021, 58(2): 0215001