[1]王道累,吴懋亮,陈军.从双视图到多视图的协同优化立体视觉匹配算法[J].华侨大学学报(自然科学版),2015,36(3):286-291.[doi:10.11830/ISSN.1000-5013.2015.03.0286]
 WANG Dao-lei,WU Mao-liang,CHEN Jun.An Algorithm of Stereo Matching Based on Cooperative Optimization from Two Views to Multiple Views[J].Journal of Huaqiao University(Natural Science),2015,36(3):286-291.[doi:10.11830/ISSN.1000-5013.2015.03.0286]
点击复制

从双视图到多视图的协同优化立体视觉匹配算法()
分享到:

《华侨大学学报(自然科学版)》[ISSN:1000-5013/CN:35-1079/N]

卷:
第36卷
期数:
2015年第3期
页码:
286-291
栏目:
出版日期:
2015-05-20

文章信息/Info

Title:
An Algorithm of Stereo Matching Based on Cooperative Optimization from Two Views to Multiple Views
文章编号:
1000-5013(2015)03-0286-06
作者:
王道累 吴懋亮 陈军
上海电力学院 能源与机械工程学院, 上海 200090
Author(s):
WANG Dao-lei WU Mao-liang CHEN Jun
College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 200090, China
关键词:
立体匹配 协同优化 图像分割 视差平面拟合
Keywords:
stereo matching cooperative optimization image segmentation disparity plane fitting
分类号:
TP391.41
DOI:
10.11830/ISSN.1000-5013.2015.03.0286
文献标志码:
A
摘要:
采用基于视图协同优化算法解决视觉匹配问题,通过对双视图立体匹配的研究到多视图匹配的推广,利用视差平面拟合进行多个视差集的合并.利用奇异值分解法解决线性方程,建立排除异常点的判别规则,解决遮挡及稀疏纹理的问题.实验结果表明:该协同优化算法是有效的,提高了匹配的精度.
Abstract:
The algorithm of stereo matching using cooperative optimization is developed to extract disparity map from image pairs. The procedure of algorithm is generally extended to apply to multiple views from two views. The disparity sets are merged into one by the disparity plane estimation, and the linear equation is solved by singular value decomposition(SVD). And the rules are built to filter out outliers, which can effectively handle the problem of occlusion and textureless. The experimental results show that the effectiveness of our proposal methods and the accurateness of stereo matching.

参考文献/References:

[1] MARR D,POGGIO T.A computational theory of human stereo vision[C]//Proceedings of the Royal Society of London.London:IEEE Press,1979:301-328.
[2] FAUGERAS O,LONG Q.The Geometry of multiple images[M].Cambridge:Cambridge University Press,2001:1-50.
[3] FURUKAWA Y,PONCE J.Accurate, dense, and robust multi-view steropsis[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2010,32(8):1362-1376.
[4] LHUILLIER M,QUAN Long.Aquasi-dense approach to surface reconstruction from uncalibrated images[J].Transactions on Pattern Analysis and Machine Intelligence,2005,27(3):418-433.
[5] WU Tai-pang,YEUNG S K,YA Jia-jia,et al.Quasi-dense 3D reconstruction using tensor-based multi-view stereo[C]//Computer Society Conference on Computer Vision and Pattern Recognition.San Francisco:IEEE Press,2010:1482-1489.
[6] VINH D N,DUC D N,SANG J L,et al.Local density encoding for robust stereo matching[J].IEEE Transctions on Circuits and Systems for Video Technology,2014, 24(12):2049-2062.
[7] XU Ling-feng,OSCAR C A,SUN Wen-xiu,et al.Stereo matching with optimal local adaptive radiometric compensation[J].IEEE Signal Processing Letters,2015, 22(2):131-135.
[8] WANG Dao-lei,LIM K B.Obtaining depth map form segment-based stereo matching using graph cuts[J].Journal of Visual Communication and Image Representation,2002,24(5):603-619.
[9] COMANICIU D,MEER P.Mean shift: A robust approach toward feature space analysis[J].Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619
[10] TAO H,SAWHNEY H S,KUMAR R.A global matching framework for stereo computation[C]//International Conference on Computer Vision.Vancouver:IEEE Press,2001:532-539.
[11] HUANG Xiao-fei.Cooperative optimization for energy minimization: A case study of stereo matching[EB/OL].[2014-09-23] .http://front.math.ucdavis.edu/author/X.Huang,cs.CV/071057.
[12] BLAKE A,ROTHER C,BROWN M,et al.Torr, interactive image segmentation using an adaptive GMMRF model[C]//Proceedings European Conference of Computer Vision.Prague:Czech Republic,2004:428-441.
[13] RHEMANN C,HOSNI A,BLEYER M C,et al.Gelautz fast cost-volume filtering for visual correspondence and beyond[C]//Conference on Computer Vision and Pattern Recognition.Colorado Springs:IEEE Press,2011:3017-3024.
[14] MEI Xing,SUN Xun,DONG Wei-ming,el at.Segment-tree based cost aggregation for stereo matching[C]//IEEE Conference on Computer Vision and Pattern Recognition.Portland:IEEE Press,2013:23-28.

备注/Memo

备注/Memo:
收稿日期: 2015-05-07
通信作者: 王道累(1981-),男,讲师,博士,主要从事计算机视觉、图像处理和CAD/CAM的研究.E-mail:alfredwdl@shiep.edu.cn.
基金项目: 上海发电环保工程技术研究中心项目(11DZ2281700)
更新日期/Last Update: 2015-05-20