首页 > 论文 > 激光与光电子学进展 > 56卷 > 15期(pp:151501--1)

一种基于边缘约束迭代的非局部立体匹配算法

Non-Local Stereo Matching Algorithm Based on Edge Constraint Iteration

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对立体匹配算法在图像非遮挡区域,尤其是弱纹理区域匹配精度较低的问题,提出一种基于边缘约束迭代的非局部立体匹配算法。该算法结合颜色和梯度信息构建匹配代价计算函数;根据左右目图像分别构建最小生成树,结合图像平滑度对代价函数值进行代价聚集,并对赢者通吃策略得到的视差图进行边缘检测,将图像边缘作为约束性条件对代价值再次进行代价聚集以优化结果;最后通过视差求精得到稠密的视差图。实验结果表明,在Middlebury测试平台上该算法对31组标准图像对中非遮挡区域的平均误匹配率为8.35%;与其他5种方法比较可知,本文算法有效提高了非遮挡区域匹配的准确度。

Abstract

To address the problem of stereo matching algorithms having low matching accuracy in non-occluded regions, especially in the weak-textured regions, a non-local stereo matching algorithm based on edge constraint iteration was proposed. Firstly, the proposed method combined the color and gradient information to construct a matching cost computation function. Secondly, the minimum spanning tree structures of left and right images were constructed, and the cost volumes were aggregated according to the smoothness information of the image. Subsequently, a disparity map obtained by the winner-takes-all strategy was used for edge detection. The image edges were then used as constraints to re-aggregate the cost volumes and optimize the results. Finally, dense disparity maps were obtained by the disparity refinement process. The experimental results demonstrate that, for 31 pairs of images from the Middlebury test platform, the average mismatching rate in non-occluded regions of the proposed algorithm is 8.35%. Compared with five existing methods, the proposed algorithm can effectively improve matching accuracy in non-occluded regions.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.151501

所属栏目:机器视觉

基金项目:国家自然科学基金(41306089);

收稿日期:2019-01-18

修改稿日期:2019-02-27

网络出版日期:2019-08-01

作者单位    点击查看

罗颖:河海大学物联网工程学院, 江苏 常州 213022
霍冠英:河海大学物联网工程学院, 江苏 常州 213022江苏省常州市传感网与环境感知重点实验室, 江苏 常州 213022
许金鑫:河海大学物联网工程学院, 江苏 常州 213022
李庆武:河海大学物联网工程学院, 江苏 常州 213022江苏省常州市传感网与环境感知重点实验室, 江苏 常州 213022

联系人作者:霍冠英(huoguanying@163.com)

备注:国家自然科学基金(41306089);

【1】Jiang X D, Yu J Y, Zhu L K et al. Self-calibrated binocular ranging system based on hardware SURF algorithm. Acta Optica Sinica. 38(10), (2018).
蒋晓东, 于纪言, 朱立坤 等. 基于硬件SURF算法的自校准双目测距系统. 光学学报. 38(10), (2018).

【2】Li D H, Shen H Y, Yu X et al. Binocular ranging method using stereo matching based on improved Census transform. Laser & Optoelectronics Progress. 56(11), (2019).
李大华, 沈洪宇, 于晓 等. 一种改进Census变换的双目匹配测距方法. 激光与光电子学进展. 56(11), (2019).

【3】Wang Q L, Li J Y and Shen H K. Target tracking system of binocular vision and laser range sensor. Acta Optica Sinica. 36(9), (2016).
王琪龙, 李建勇, 沈海阔. 双目视觉-激光测距传感器目标跟踪系统. 光学学报. 36(9), (2016).

【4】Wang S and Xu X. 3D reconstruction based on horopter. Acta Optica Sinica. 37(5), (2017).
王珊, 徐晓. 基于双目单视面的三维重建. 光学学报. 37(5), (2017).

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

【6】Wang K, Li Z W, Zhu C D et al. Local stereo matching algorithm based on secondary guided filtering. Laser & Optoelectronics Progress. 56(8), (2019).
王凯, 李志伟, 朱成德 等. 基于二次引导滤波的局部立体匹配算法. 激光与光电子学进展. 56(8), (2019).

【7】Yan L, Wang R, Liu H et al. Stereo matching method based on improved cost computation and adaptive guided filter. Acta Optica Sinica. 38(11), (2018).
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. 光学学报. 38(11), (2018).

【8】Yoon K J and Kweon I S. Adaptive support-weight approach for correspondence search. IEEE Transactions on Pattern Analysis and Machine Intelligence. 28(4), 650-656(2006).

【9】Su X, Chen X D, Xu H Y et al. Adaptive window local matching algorithm based on HSV color space. Laser & Optoelectronics Progress. 55(3), (2018).
苏修, 陈晓冬, 徐怀远 等. 基于HSV颜色空间的自适应窗口局部匹配算法. 激光与光电子学进展. 55(3), (2018).

【10】Sun J, Zheng N N and Shum H Y. Stereo matching using belief propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 25(7), 787-800(2003).

【11】Klaus A, Sormann M and Karner K. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. [C]∥18th International Conference on Pattern Recognition (ICPR''06), August 20-24, 2006, Hong Kong, China. New York: IEEE. 9209946, (2006).

【12】Boykov Y, Veksler O and Zabih R. Fast approximate energy minimization via graph cuts. [C]∥Proceedings of the Seventh IEEE International Conference on Computer Vision, September 20-27, 1999, Kerkyra, Greece. New York: IEEE. 6365236, (1999).

【13】Wang H Q, Wu M, Zhang Y B et al. Effective stereo matching using reliable points based graph cut. [C]∥2013 Visual Communications and Image Processing (VCIP), November 17-20, 2013, Kuching, Malaysia. New York: IEEE. 14028712, (2013).

【14】Zhang S H, He H and Kong L F. Fusing multi-feature for video occlusion region detection based on graph cut. Acta Optica Sinica. 35(4), (2015).
张世辉, 何欢, 孔令富. 融合多特征基于图割实现视频遮挡区域检测. 光学学报. 35(4), (2015).

【15】Bleyer M and Gelautz M. Simple but effective tree structures for dynamic programming-based stereo matching. [C]∥Proceedings of the Third International Conference on Computer Vision Theory and Applications, January 22-25, 2008, Funchal, Madeira, Portugal. [S.l.]: [s.n.]. 415-422(2008).

【16】Salehian B, Fotouhi A M and Raie A A. Dynamic programming-based dense stereo matching improvement using an efficient search space reduction technique. Optik. 160, 1-12(2018).

【17】Zhu S P, Yan L N and Li Z. Stereo matching algorithm based on improved Census transform and dynamic programming. Acta Optica Sinica. 36(4), (2016).
祝世平, 闫利那, 李政. 基于改进Census变换和动态规划的立体匹配算法. 光学学报. 36(4), (2016).

【18】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: IEEE. 467-474(2011).

【19】Xu J X, Li Q W, Liu Y et al. Stereo matching algorithm based on color weights and tree dynamic programming. Acta Optica Sinica. 37(12), (2017).
许金鑫, 李庆武, 刘艳 等. 基于色彩权值和树形动态规划的立体匹配算. 光学学报. 37(12), (2017).

【20】Yang Q X. Stereo matching using tree filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence. 37(4), 834-846(2015).

【21】Mei X, Sun X, Dong W M et al. Segment-tree based cost aggregation for stereo matching. [C]∥2013 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2013, Portland, OR, USA. New York: IEEE. 313-320(2013).

【22】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 (CVPR), June 23-28, 2014, Columbus, OH, USA. New York: IEEE. 1590-1597(2014).

【23】Yao P, Zhang H, Xue Y B et al. Iterative color-depth MST cost aggregation for stereo matching. [C]∥2016 IEEE International Conference on Multimedia and Expo (ICME), July 11-15, 2016, Seattle, WA, USA. New York: IEEE. 16266824, (2016).

【24】Gao S Y, Ge H H, Zhang H et al. A nonlocal method with modified initial cost and multiple weight for stereo matching. Journal of Sensors. 2017, (2017).

【25】Gerrits M and Bekaert P. Local stereo matching with segmentation-based outlier rejection. [C]∥The 3rd Canadian Conference on Computer and Robot Vision (CRV''06), June 7-9, 2006, Quebec, Canada. New York: IEEE. (2006).

【26】Huang X M and Zhang Y J. An O(1) disparity refinement method for stereo matching. Pattern Recognition. 55, 198-206(2016).

【27】Yang Q Q. Local smoothness enforced cost volume regularization for fast stereo correspondence. IEEE Signal Processing Letters. 22(9), 1429-1433(2015).

引用该论文

Ying Luo, Guanying Huo, Jinxin Xu, Qingwu Li. Non-Local Stereo Matching Algorithm Based on Edge Constraint Iteration[J]. Laser & Optoelectronics Progress, 2019, 56(15): 151501

罗颖, 霍冠英, 许金鑫, 李庆武. 一种基于边缘约束迭代的非局部立体匹配算法[J]. 激光与光电子学进展, 2019, 56(15): 151501

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF