基于跨尺度代价聚合的改进立体匹配算法

doi:10.3969/j.issn.1000-3428.2016.11.045

计算机工程

基于跨尺度代价聚合的改进立体匹配算法

汤春明,蒋昂

(天津工业大学电子与信息工程学院,天津 300387)

收稿日期:2015-10-09 出版日期:2016-11-15 发布日期:2016-11-15
作者简介:汤春明(1971—),女,教授、博士生导师,主研方向为图像处理、目标识别与跟踪;蒋昂,硕士研究生。
基金资助:
天津市第三批“三年千人”计划项目(62014511);天津工业大学高层次人才及教师引进计划项目(030367)。

Improved Stereo Matching Algorithm Based on Cross-scale Cost Aggregation

TANG Chunming,JIANG Ang

(School of Electronic and Information Engineering,Tianjin Polytechnic University,Tianjin 300387,China)

Received:2015-10-09 Online:2016-11-15 Published:2016-11-15

摘要/Abstract

摘要： 针对现有的立体匹配算法在精度和速度上不可兼得的现状,提出一种改进的跨尺度代价聚合立体匹配算法。通过强度和梯度算法计算匹配代价,利用引导滤波聚合匹配代价,采用跨尺度模型聚合各尺度的匹配代价,使用补丁匹配近似算法代替传统胜者为王算法求取初始视差,并在视差细化阶段采用快速加权中值滤波进行后续处理。实验结果表明,该算法能在快速获得视差图的同时提高匹配精度。

关键词: 立体匹配算法, 跨尺度模型, 代价聚合, 引导滤波, 快速加权中值滤波

Abstract: An improved algorithm is proposed based on cross-scale cost aggregation for stereo matching because the existing stereo matching algorithms cannot take both accuracy and speed into account.Firstly the matching cost volume is computed by the intensity and gradient algorithm.Then the matching cost volume is aggregated by guide filtering and the matching cost volume of different scales is aggregated by the cross-scale model.The patch matching approximation algorithm is used instead of the traditional Winner Taker All(WTA) algorithm to calculate the initial parallax,and the weighted median filtering is adopted for subsequent processing in parallax elaboration.Experimental results show that the algorithm can rapidly obtain the disparity map and also improve the matching accuracy.

Key words: stereo matching algorithm, cross-scale model, cost aggregation, guided filtering, fast weighted median filtering

中图分类号:

TP391.4

汤春明,蒋昂. 基于跨尺度代价聚合的改进立体匹配算法[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2016.11.045.

TANG Chunming,JIANG Ang. Improved Stereo Matching Algorithm Based on Cross-scale Cost Aggregation[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2016.11.045.

https://www.ecice06.com/CN/Y2016/V42/I11/272

参考文献

参考文献［1］Liu Ce,Jenny Yuen,Antonio T.SIFT Flow:Dense Correspondence Across Scenes and Its Applications［J］.IEEE Biometrics Compendium,2011,33(5):978-994. ［2］李娇,钱惟贤,陈钱,等.一种基于贝叶斯理论的高效立体匹配方法［J］.激光与光电子学进展,2014,51(10):75-82. ［3］Tomasi C,Manduchi R.Bilateral Filtering for Gray and Color Images［C］//Proceedings of the 6th International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,1998:839-846. ［4］He Kaiming,Sun Jian,Tang Xiaoou.Guided Image Filtering［J］.IEEE Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409. ［5］Kuk-Jin Y,Kweon I S.Adaptive Support-weight Approach for Correspondence Search［J］.IEEE Pattern Analysis and Machine Intelligence,2006,28(4):650-656. ［6］Rhemann C,Hosni A,Bleyer M,et al.Fast Cost-volume Filtering for Visual Correspondence and Beyond［J］.IEEE Pattern Analysis and Machine Intelligence,2013,35(2):504-511. ［7］Yang Qingxiong.A Non-local Cost Aggregation Method for Stereo Matching［C］//Proceedings of Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:1402-1409. ［8］Mei Xing,Sun Xun,Dong Weiming,et al.Segment-tree Based Cost Aggregation for Stereo Matching［C］//Proceedings of Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:313-320. ［9］Zhang Kang,Fang Yuqiang,Min Dongbo,et al.Cross-scale Cost Aggregation for Stereo Matching［C］//Proceedings of Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:1590-1597. ［10］Huang T,Yang G,Tang G.A Fast Two-dimensional Median Filtering Algorithm［J］.IEEE Acoustics,Speech and Signal Processing,1979,27(1):13-18. ［11］王玮.基于遮挡信息的局部立体匹配算法的研究［D］.济南:山东大学,2012. ［12］Mattoccia S.A Locally Global Approach to Stereo Corres-pondence［C］//Proceedings of International Conference on Computer Vision Workshops.Washington D.C.,USA:IEEE Press,2009:1763-1700. (下转第280页) (上接第276页) ［13］Hirschmüller H.Stereo Processing by Semi-global Matching and Mutual Information［J］.IEEE Pattern Analysis and Machine Intelligence,2008,30(2):328-341. ［14］Wang Zengfu,Zheng Zhigang.A Region Based Stereo Matching Algorithm Using Cooperative Optimization［C］//Proceedings of Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1-8. ［15］Ma Ziyang,He Kaiming,Wei Yichen,et al.Constant Time Weighted Median Filtering for Stereo Matching and Beyond［C］//Proceedings of International Con-ference on Computer Vision.Washington D.C.,USA:IEEE Press,2013:49-56. ［16］张华,刘宏立,徐琨,等.基于跨尺度变窗口代价聚合的快速立体匹配［J］.计算机工程与应用,2015,51(17):151-156. ［17］Zhang Qi,Xu Li,Jia Jiaya.100+Times Faster Weighted Median Filter (WMF)［C］//Proceedings of Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:2830-2837. 编辑刘冰

[1]	史艳琼, 查昭, 张文亮, 戴尔愉, 陈中. 基于深度估计置信度的聚焦形貌恢复[J]. 计算机工程, 2024, 50(3): 233-241.
[2]	余嘉昕, 王春媛, 韩华, 高燕. 基于融合代价和优化引导滤波的立体匹配算法[J]. 计算机工程, 2023, 49(3): 257-262,270.
[3]	乔彩彩, 吴成茂, 李昌兴, 王佳烨. 结合隶属度与像素交替引导滤波的鲁棒模糊聚类算法[J]. 计算机工程, 2022, 48(8): 224-233.
[4]	陈子妍, 龙道银, 王霄, 覃涛, 杨靖. 基于逆通道与改进引导滤波的暗通道去雾算法[J]. 计算机工程, 2021, 47(6): 245-252.
[5]	郭伟, 洪倩. 基于边界和中心关系的显著性检测方法[J]. 计算机工程, 2020, 46(6): 241-247.
[6]	向文鼎, 杨平, 许冰. 基于自适应阈值分割与透射率融合的图像去雾算法[J]. 计算机工程, 2019, 45(10): 239-245.
[7]	张万绪,史剑雄,陈晓璇,汪霖,赵明,周延,牛进平. 基于稀疏表示与引导滤波的图像超分辨率重建[J]. 计算机工程, 2018, 44(9): 212-217.
[8]	董亚运,毕笃彦,何林远,眭萍. 基于双向耦合的单幅图像快速去雾算法[J]. 计算机工程, 2017, 43(10): 246-252,258.
[9]	杨燕,白海平,王帆. 基于引导滤波的单幅图像自适应去雾算法[J]. 计算机工程, 2016, 42(1): 265-271.
[10]	杨燕,白海平. 基于暗通道先验的补偿快速去雾算法[J]. 计算机工程, 2015, 41(10): 210-215,220.
[11]	杨军，张瑞峰，王小鹏，林岩龙. 基于图像引导滤波的人脸光照预处理算法[J]. 计算机工程, 2014, 40(4): 182-186,191.

选择文件类型/文献管理软件名称

选择包含的内容

基于跨尺度代价聚合的改进立体匹配算法

Improved Stereo Matching Algorithm Based on Cross-scale Cost Aggregation

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于跨尺度代价聚合的改进立体匹配算法

Improved Stereo Matching Algorithm Based on Cross-scale Cost Aggregation

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价