结合局部二进制表示和超像素分割求精的立体匹配
|
摘要
为改善传统立体匹配视差图中目标边缘的毛刺现象,以及弱纹理和视差不连续区域的"阶梯效应"等,提出了一种结合局部二进制表示和超像素分割的立体匹配方法。首先融合二进制表示的窗口内像素的空间和颜色特征进行代价计算,并以此求得初始视差;然后将简单线性迭代聚类方法分割的结果作为像素的空间和颜色标记,为超像素内的目标边缘和其他像素点选择恰当的稳定点进行视差传播,以达到视差优化时边缘保持和空间平滑的目的。在Middlebury数据集上分别进行代价计算与优化方法的对比实验,结果表明,采用该算法获取的目标边缘的视差更为平滑,在左右视图中的遮挡区和不重叠区域获得的视差也比较准确,有效地降低了非遮挡区、全图、不连续区域的误匹配率。
In order to polish up the target edge burring and staircase effect in low-textured regions or discontinuous regions,a stereo matching method based on the local binary description and superpixel segmentation is proposed.Firstly,the initial disparity is obtained by space and color features binary cost computation and winner-takes-all method.Then the segmentation results by simple linear iterative clustering method are labeled for each pixel's space and color features.In disparity refinement procedure,the appropriate fixed points are chosen to propagate disparity for both edge and inner pixels of each superpixel.Experiments with Middlebury datasets are mainly carried out in the initial disparity considerations and disparity refinement.The result shows that the disparity maps are much smoother especially in target boundary.The proposed method can achieve more accurate disparity value in nonoverlapping and occluded regions between reference image and matching image,which effectively reduces the mismatching rate in non-occluded,all,and discontinuity regions.
In order to polish up the target edge burring and staircase effect in low-textured regions or discontinuous regions,a stereo matching method based on the local binary description and superpixel segmentation is proposed.Firstly,the initial disparity is obtained by space and color features binary cost computation and winner-takes-all method.Then the segmentation results by simple linear iterative clustering method are labeled for each pixel's space and color features.In disparity refinement procedure,the appropriate fixed points are chosen to propagate disparity for both edge and inner pixels of each superpixel.Experiments with Middlebury datasets are mainly carried out in the initial disparity considerations and disparity refinement.The result shows that the disparity maps are much smoother especially in target boundary.The proposed method can achieve more accurate disparity value in nonoverlapping and occluded regions between reference image and matching image,which effectively reduces the mismatching rate in non-occluded,all,and discontinuity regions.
引文
[1]Shan B H,Huo X Y,Liu Y.A stereovision measurement method using epipolar constraint to correct digital image correlation matching[J].Chinese Journal of Lasers,2017,44(8):0804003.单宝华,霍晓洋,刘洋.一种极线约束修正数字图像相关匹配的立体视觉测量方法[J].中国激光,2017,44(8):0804003.
[2]Yang Q,Wang L,Yang R,et al.Stereo matching with color-weighted correlation,hierarchical belief propagation,and occlusion handling[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(3):492-504.
[3]Taniai T,Matsushita Y,Sato Y,et al.Continuous3D label stereo matching using local expansion moves[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017:1-20.
[4]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,2011,21(5):467-474.
[5]Ji Y H,Ma L Z.Stability-based tree for disparity refinement[J].Journal of Computer-Aided Design&Computer Graphics,2016,28(12):2159-2167.季雨航,马利庄.基于稳定树的立体匹配视差优化算法[J].计算机辅助设计与图形学学报,2016,28(12):2159-2167.
[6]Yao P,Zhang H,Xue Y,et al.Iterative color-depth MST cost aggregation for stereo matching[C].IEEE International Conference on Multimedia and Expo,2016:1-6.
[7]Hamzah R A,Ibrahim H.Literature survey on stereo vision disparity map algorithms[J].Journal of Sensors,2016,2:1-23.
[8]Lin C H,Liu C W.Accurate stereo matching0615003-8algorithm based on cost aggregation with adaptive support weight[J].The Imaging Science Journal,2015,63(8):423-432.
[9]Guo S,Xu P,Zheng Y.Semi-global matching based disparity estimate using fast Census transform[C].International Congress on Image and Signal Processing,Biomedical Engineering and Informatics,2017:548-552.
[10]Zhu S P,Yan L N,Li Z.A stereo matching algorithm using improved gradient and adaptive window[J].Acta Optica Sinica,2016,36(4):0415001.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[J].光学学报,2016,36(4):0415001.
[11]Peng X J,Han J,Tang Y,et al.Anti-noise stereo matching algorithm based on improved Census transform and outlier elimination[J].Acta Optica Sinica,2017,37(11):1115004.彭新俊,韩军,汤踊,等.基于改进Census变换和异常值剔除的抗噪立体匹配算法[J].光学学报,2017,37(11):1115004.
[12]Zhang K,Li J,Li Y,et al.Binary stereo matching[C].21st International Conference on Pattern Recognition,2012:356-359.
[13]Lee S,Lee J H,Lim J,et al.Robust stereo matching using adaptive random walk with restart algorithm[J].Image and Vision Computing,2015,37:1-11.
[14]Calonder M,Lepetit V,Strecha C,et al.Brief:binary robust independent elementary features[C].European Conference on Computer Vision,2010,6314:778-792.
[15]Achanta R,Shaji A,Smith K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[16]Scharstein D,Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].International Journal of Computer Vision,2002,47(1/2/3):7-42.
[17]Lee J,Jun D,Eem C,et al.Improved Census transform for noise robust stereo matching[J].Optical Engineering,2016,55(6):063107.
[18]Yang Q.Stereo matching using tree filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(4):834-846.
[19]Yang Q.Local smoothness enforced cost volume regularization for fast stereo correspondence[J].IEEE Signal Processing Letters,2015,22(9):1429-1433.
[2]Yang Q,Wang L,Yang R,et al.Stereo matching with color-weighted correlation,hierarchical belief propagation,and occlusion handling[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(3):492-504.
[3]Taniai T,Matsushita Y,Sato Y,et al.Continuous3D label stereo matching using local expansion moves[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017:1-20.
[4]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,2011,21(5):467-474.
[5]Ji Y H,Ma L Z.Stability-based tree for disparity refinement[J].Journal of Computer-Aided Design&Computer Graphics,2016,28(12):2159-2167.季雨航,马利庄.基于稳定树的立体匹配视差优化算法[J].计算机辅助设计与图形学学报,2016,28(12):2159-2167.
[6]Yao P,Zhang H,Xue Y,et al.Iterative color-depth MST cost aggregation for stereo matching[C].IEEE International Conference on Multimedia and Expo,2016:1-6.
[7]Hamzah R A,Ibrahim H.Literature survey on stereo vision disparity map algorithms[J].Journal of Sensors,2016,2:1-23.
[8]Lin C H,Liu C W.Accurate stereo matching0615003-8algorithm based on cost aggregation with adaptive support weight[J].The Imaging Science Journal,2015,63(8):423-432.
[9]Guo S,Xu P,Zheng Y.Semi-global matching based disparity estimate using fast Census transform[C].International Congress on Image and Signal Processing,Biomedical Engineering and Informatics,2017:548-552.
[10]Zhu S P,Yan L N,Li Z.A stereo matching algorithm using improved gradient and adaptive window[J].Acta Optica Sinica,2016,36(4):0415001.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[J].光学学报,2016,36(4):0415001.
[11]Peng X J,Han J,Tang Y,et al.Anti-noise stereo matching algorithm based on improved Census transform and outlier elimination[J].Acta Optica Sinica,2017,37(11):1115004.彭新俊,韩军,汤踊,等.基于改进Census变换和异常值剔除的抗噪立体匹配算法[J].光学学报,2017,37(11):1115004.
[12]Zhang K,Li J,Li Y,et al.Binary stereo matching[C].21st International Conference on Pattern Recognition,2012:356-359.
[13]Lee S,Lee J H,Lim J,et al.Robust stereo matching using adaptive random walk with restart algorithm[J].Image and Vision Computing,2015,37:1-11.
[14]Calonder M,Lepetit V,Strecha C,et al.Brief:binary robust independent elementary features[C].European Conference on Computer Vision,2010,6314:778-792.
[15]Achanta R,Shaji A,Smith K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[16]Scharstein D,Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].International Journal of Computer Vision,2002,47(1/2/3):7-42.
[17]Lee J,Jun D,Eem C,et al.Improved Census transform for noise robust stereo matching[J].Optical Engineering,2016,55(6):063107.
[18]Yang Q.Stereo matching using tree filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(4):834-846.
[19]Yang Q.Local smoothness enforced cost volume regularization for fast stereo correspondence[J].IEEE Signal Processing Letters,2015,22(9):1429-1433.