计算机科学 ›› 2019, Vol. 46 ›› Issue (11A): 241-245.

• 模式识别与图像处理 • 上一篇    下一篇

基于改进多权值滑动窗口的立体匹配方法的实现及应用

杜娟, 沈思昀   

  1. (华南理工大学 广州510641)
  • 出版日期:2019-11-10 发布日期:2019-11-20
  • 通讯作者: 杜娟(1975-),女,博士,副教授,主要研究方向为图像检测、机器视觉、智能控制,E-mail:dujuan@scut.edu。
  • 基金资助:
    本文受广东省自然科学基金(2016A030313454),广州市科学与技术基金(201707010061),广州市南沙区科学与技术基金(2016GJ012)资助。

Implementation and Application of Stereo Matching Method Based onImproved Multi-weight Sliding Window

DU Juan, SHEN Si-yun   

  1. (South China University of Technology,Guangzhou 510641,China)
  • Online:2019-11-10 Published:2019-11-20

摘要: 立体视觉的核心问题是通过立体匹配算法获得准确的视差值,然而大多数现有的立体匹配算法无法在低纹理或接近无纹理的区域中获得准确的视差值。为了解决低纹理区域匹配精度相对偏低、高精度半全局匹配算法运算量较大的问题,文中提出了一种基于自适应滑动窗口的立体匹配算法。首先通过AD-Census变换计算匹配代价,然后针对不同区域调节聚合窗口形状及像素点权重,最后结合符合人体视觉特征的多尺度代价聚合框架获得聚合匹配代价,采用赢者通吃策略获取最终的稠密视差图。实验结果证明,该算法在低纹理区域的误匹配率相比较传统方案的下降范围为5.8%~21.68%,运算时间较半全局算法更短。

关键词: AD-Census变换, 高斯金字塔, 立体匹配, 自适应滑动窗口

Abstract: The key problem of stereo vision is to obtain accurate disparity values through stereo matching algorithms.However,most existing stereo matching algorithms are unable to obtain accurate and correct disparities in low-texture regions.In this paper,in order to solve the problems of low matching accuracy of low texture regions and large computational complexity of high-precision semi-global matching algorithm,a stereo matching algorithm based on adaptive sliding window was proposed.The cost volume is calculated by AD-Census transform firstly.The shape of the aggregate window and the weight of the pixels are adjusted for different regions.The cross-scale cost aggregation framework conforming to the human visual feature is used to obtain the aggregate cost volume.Finally,the “winner take all strategy” is used to obtain the final disparity maps.Experiments show that the mismatch rate of the algorithm in low-texture regions decrease form 5.8% to 21.68%,which is lower than that of the traditional scheme,and the computation time is shorter than the semi-global algorithm.

Key words: Adaptive sliding window, AD-Census transform, Gaussian pyramid, Stereo matching

中图分类号: 

  • TP391
[1]YANG Q,WANG L,YANG R,et al.Stereo Matching with Color-Weighted Correlation,Hierachical Belief Propagation and Occlusion Handling[C]∥IEEE Computer Society Conference on Computer Vision & Pattern Recognition.IEEE Computer Society,2006.
[2]HONG L,CHEN G.Segment-Based Stereo Matching UsingGraph Cuts[C]∥null.IEEE Computer Society,2004.
[3]HIRSCHM H.Stereo Processing by Semi-global Matching and Mutual Information[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,30(2):328-341.
[4]ŽBONTAR,JURE,LECUN Y.Computing the Stereo Matching Cost with a Convolutional Neural Network[J].Computer Vision and Pattern Recognition,2014.
[5]YANG Q.Stereo Matching Using Tree Filtering[J].IEEETransactions on Pattern Analysis & Machine Intelligence,2015.
[6]HE K,JIAN S,TANG X.Guided Image Filtering[M]∥Computer Vision- ECCV 2010.2010.
[7]KANADE T,OKUTOMI M.A stereo matching algorithm with an adaptive window:theory and experiment[C]∥IEEE International Conference on Robotics & Automation.IEEE,2002.
[8]ZABIH R,WOODFILL J.Non-parametric Local Transforms for Computing Visual Correspondence[J].Proc.third European Conf.computer Vision,1994:151-158.
[9]SHEN Y.Efficient normalized cross correlation calculationmethod for stereo vision based robot navigation[J].中国计算机科学前沿:英文版,2011,5(2):227-235.
[10]KIM J,KOLMOGORO V,ZABI H.Visual correspondence using energy minimization and mutual information[C]∥Proceedings Ninth IEEE International Conference on Computer Vision.IEEE,2008.
[11]SCHARSTEIN D,SZELISKI R.A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms[J].International Journal of Computer Vision,2002,47(1/3):7-42.
[12]VEKSLER O.Fast variable window for stereo correspondence using integral images[C]∥2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003.IEEE,2003.
[13]YOON K J,KWEON I S.Adaptive Support-Weight Approach for Correspondence Search[J].IEEE Trans Pattern Anal Mach Intell,2006.
[14]ZHANG K,LU J,LAFUIT 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.
[15]YANG Q.A non-local cost aggregation method for stereo matching[C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2012.
[16]MEI X,SUN X,DONG W,et al.Segment-Tree Based Cost Aggregation for Stereo Matching[C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2013.
[17]MEI X,SUN X,ZHOU M,et al.On building an accurate stereo matching system on graphics hardware[C]∥IEEE International Conference on Computer Vision Workshops.2012.
[18]LOWE D G.Distinctive Image Features from Scale-InvariantKeypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[19]ZHANG K,FANG Y,MIN D,et al.Cross-Scale Cost Aggregation for Stereo Matching[C]∥Computer Vision & Pattern Recognition.IEEE,2014.
[1] 封雷, 朱登明, 李兆歆, 王兆其.
一种基于遮罩的稀疏点云滤波算法
Sparse Point Cloud Filtering Algorithm Based on Mask
计算机科学, 2022, 49(5): 25-32. https://doi.org/10.11896/jsjkx.210600129
[2] 张鹏, 王新晴, 肖毅, 段宝国, 许鸿辉.
基于语义边缘驱动的实时双目深度估计算法
Real-time Binocular Depth Estimation Algorithm Based on Semantic Edge Drive
计算机科学, 2021, 48(9): 216-222. https://doi.org/10.11896/jsjkx.200800203
[3] 曹林, 于威威.
基于图像分割的自适应窗口双目立体匹配算法研究
Adaptive Window Binocular Stereo Matching Algorithm Based on Image Segmentation
计算机科学, 2021, 48(11A): 314-318. https://doi.org/10.11896/jsjkx.201200264
[4] 桑苗苗, 彭进先, 达通航, 张旭峰.
基于PatchMatch的半全局高效双目立体匹配算法
Efficient Semi-global Binocular Stereo Matching Algorithm Based on PatchMatch
计算机科学, 2021, 48(1): 204-208. https://doi.org/10.11896/jsjkx.191000205
[5] 朱玲莹, 桑庆兵, 顾婷婷.
基于视差信息的无参考立体图像质量评价
No-reference Stereo Image Quality Assessment Based on Disparity Information
计算机科学, 2020, 47(9): 150-156. https://doi.org/10.11896/jsjkx.190700213
[6] 李银国, 周中奎, 白羚.
基于双目图像的大尺度智能驾驶场景重建
Large-scale Automatic Driving Scene Reconstruction Based on Binocular Image
计算机科学, 2019, 46(11A): 251-254.
[7] 江泽涛, 王琦, 赵艳.
一种基于自适应支持权重优化的立体匹配算法
Stereo Matching Algorithm Based on Adaptive Support Weight Optimization
计算机科学, 2018, 45(8): 242-246. https://doi.org/10.11896/j.issn.1002-137X.2018.08.043
[8] 张彦峰,黄向生,李杭,王梦伟.
基于渐进可靠点生长的散斑图快速立体匹配
Fast Stereo Matching Based on Progressive Reliable Point Growing Matching for Speckle Pattern Images
计算机科学, 2014, 41(Z6): 143-146.
[9] 曾凡志,鲍苏苏.
一种自适应多窗口的立体匹配算法
Adaptive Multiple Windows Stereo Matching Algorithm
计算机科学, 2012, 39(Z6): 519-521.
[10] 呼艳,耿国华,周明全,王小凤.
基于未标定彩色图像三维重建的立体匹配算法
Stereo Matching Algorithm Based on Uncalibrated Color Images for 3D Reconstruction
计算机科学, 2011, 38(7): 277-279.
[11] .
一种新的非参数变换定义及立体匹配方法

计算机科学, 2009, 36(2): 190-193.
[12] 卢思军,唐振民,郭龙源,卢阿丽.
存在镜面反射时的立体匹配研究
Research on Binocular Stereo Matching in the Presence of Specular Reflections
计算机科学, 2009, 36(11): 266-268.
[13] 陈旺,张茂军,熊志辉.
基于区域边界约束和图割优化的稠密匹配算法
Dense Matching Algorithm Based on Region Boundary Restriction via Graph Cuts Optimization
计算机科学, 2009, 36(11): 258-261.
[14] 卢阿丽 唐振民 杨静宇.
一种基于方向能量聚集的立体匹配算法

计算机科学, 2008, 35(4): 186-189.
[15] .
非参量变换在彩色图像立体匹配中的应用研究

计算机科学, 2008, 35(11): 217-219.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!