加权约束代价聚合的立体匹配算法
|
摘要
针对动态规划立体匹配算法存在的条纹瑕疵问题,提出了一种加权约束代价聚合的立体匹配算法。首先利用图像灰度与梯度信息联合计算匹配代价,并进行引导图像滤波;再通过四方向加权代价聚合的方式进行视差优化,得到最终视差图。标准测试数据实验结果证明,该算法能很好地改善传统动态规划算法的条纹瑕疵现象,且视差精度优于多数局部算法和动态规划改进算法,提高了立体匹配的精度。
A stereo matching algorithm of weighting constraint cost aggregation was proposed to solve stripe detect problem in dynamic programming stereo matching algorithm in this paper.Firstly,we used the image gray level and gradient information to calculate the matching cost,and conducted guided image filtering.And then,we used the four-direction weighting cost aggregation algorithm to carry on parallax error optimization,and acquired the final parallax error image.The experiment results of standard test data show that this algorithm could improve the stripe defect problem in the traditional dynamic programming algorithm,and its parallax error accuracy is better than the most local and dynamic programming improved algorithms,which can raise the accuracy of stereo matching.
A stereo matching algorithm of weighting constraint cost aggregation was proposed to solve stripe detect problem in dynamic programming stereo matching algorithm in this paper.Firstly,we used the image gray level and gradient information to calculate the matching cost,and conducted guided image filtering.And then,we used the four-direction weighting cost aggregation algorithm to carry on parallax error optimization,and acquired the final parallax error image.The experiment results of standard test data show that this algorithm could improve the stripe defect problem in the traditional dynamic programming algorithm,and its parallax error accuracy is better than the most local and dynamic programming improved algorithms,which can raise the accuracy of stereo matching.
引文
[1]PENG Y,LI G,WANG R,et al.Stereo Matching with Spaceconstrained Cost Aggregation and Segmentation-based Disparity Refinement[J].Proceedings of SPIE-the International Society for Optical Engineering,2015(9393):11
[2]Scharstein D,Szeliski R,Zabih R.A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms[J].International Journal of Computer Vision,2002,47(1/3):7-42
[3]Bobick A F,Intille S S.Large Occlusion Stereo[J].International Journal of Computer Vision,1999,33(3):181-200
[4]Veksler O.Stereo Correspondence by Dynamic Programming on a Tree[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:384-390
[5]YANG Q.A Non-local Cost Aggregation Method for Stereo Matching[C].IEEE Computer Vision and Pattern Recognition,2012:1 402-1 409
[6]Felzenszwalb P F,Huttenlocher D P.Efficient Belief Propagation for Early Vision[J].International Journal of Computer Vision,2006,1(1):41-54
[7]Freeman W T,Pasztor E C,Carmichael O T.Learning Low-level Vision[J].International Journal of Computer Vision,2000,40(1):25-47
[8]SUN J,ZHENG N N,Shum H Y.Stereo Matching Using Belief Propagation[J].European Conference on Computer Vision,2002,25(7):510-524
[9]Boykov Y,Veksler O,Zabih R.Fast Approximate Energy Minimization via Graph Cuts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(11):1 222-1 239
[10]Huat T C,Bin N,Manap A.Evaluation of Stereo Matching Algorithms and Dynamic Programming for 3D Triangulation[C].Icocoe,2014:641-650
[11]王忠波.立体视觉中匹配技术的研究[D].大连:大连理工大学,2008
[12]Birchfield S,Tomasi C.Depth Discontinuities by Pixelto-Pixel Stereo[J].International Journal of Computer Vision,1999,35(3):269-293
[13]XIAO J,XIA L,LIN L,et al.A Segment-based Stereo Matching Method with Ground Control Points[C].IEEE International Conference on Environmental Science and Information Application Technology,2010:306-309
[14]CHANG X,ZHOU Z,WANG L,et al.Real-time Accurate Stereo Matching Using Modified Two-pass Aggregation and Winner-take-all Guided Dynamic Programming[C].IEEE International Conference on 3D Imaging,Modeling,Processing,Visualization and Transmission,2011:73-79
[15]ZHOU Z,WU D,ZHU Z.Stereo Matching Using Dynamic Programming Based on Differential Smoothing[J].Optikinternational Journal for Light and Electron Optics,2015,127(4):2 287-2 293
[16]HE K M,SUN J,TANG X O.Guided Image Filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1 397-1 409
[17]Hirschmuller H.Stereo Processing by Semiglobal Matching and Mutual Information[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(2):328-341
[18]MEI X,SUN X,ZHOU M C,et al.On Building an Accurate Stereo Matching System on Graphics Hardware[J].IEEE International Conference on Computer Vision Workshops,2012,21(5):467-474
[2]Scharstein D,Szeliski R,Zabih R.A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms[J].International Journal of Computer Vision,2002,47(1/3):7-42
[3]Bobick A F,Intille S S.Large Occlusion Stereo[J].International Journal of Computer Vision,1999,33(3):181-200
[4]Veksler O.Stereo Correspondence by Dynamic Programming on a Tree[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:384-390
[5]YANG Q.A Non-local Cost Aggregation Method for Stereo Matching[C].IEEE Computer Vision and Pattern Recognition,2012:1 402-1 409
[6]Felzenszwalb P F,Huttenlocher D P.Efficient Belief Propagation for Early Vision[J].International Journal of Computer Vision,2006,1(1):41-54
[7]Freeman W T,Pasztor E C,Carmichael O T.Learning Low-level Vision[J].International Journal of Computer Vision,2000,40(1):25-47
[8]SUN J,ZHENG N N,Shum H Y.Stereo Matching Using Belief Propagation[J].European Conference on Computer Vision,2002,25(7):510-524
[9]Boykov Y,Veksler O,Zabih R.Fast Approximate Energy Minimization via Graph Cuts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(11):1 222-1 239
[10]Huat T C,Bin N,Manap A.Evaluation of Stereo Matching Algorithms and Dynamic Programming for 3D Triangulation[C].Icocoe,2014:641-650
[11]王忠波.立体视觉中匹配技术的研究[D].大连:大连理工大学,2008
[12]Birchfield S,Tomasi C.Depth Discontinuities by Pixelto-Pixel Stereo[J].International Journal of Computer Vision,1999,35(3):269-293
[13]XIAO J,XIA L,LIN L,et al.A Segment-based Stereo Matching Method with Ground Control Points[C].IEEE International Conference on Environmental Science and Information Application Technology,2010:306-309
[14]CHANG X,ZHOU Z,WANG L,et al.Real-time Accurate Stereo Matching Using Modified Two-pass Aggregation and Winner-take-all Guided Dynamic Programming[C].IEEE International Conference on 3D Imaging,Modeling,Processing,Visualization and Transmission,2011:73-79
[15]ZHOU Z,WU D,ZHU Z.Stereo Matching Using Dynamic Programming Based on Differential Smoothing[J].Optikinternational Journal for Light and Electron Optics,2015,127(4):2 287-2 293
[16]HE K M,SUN J,TANG X O.Guided Image Filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1 397-1 409
[17]Hirschmuller H.Stereo Processing by Semiglobal Matching and Mutual Information[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(2):328-341
[18]MEI X,SUN X,ZHOU M C,et al.On Building an Accurate Stereo Matching System on Graphics Hardware[J].IEEE International Conference on Computer Vision Workshops,2012,21(5):467-474