基于跨尺度引导图像滤波的稠密立体匹配
|
摘要
针对现有局部立体匹配算法在弱纹理表面、深度不连续处等特定区域匹配精度低、实时性难以满足要求等问题,提出了一种基于跨尺度引导图像滤波的稠密立体匹配算法。利用图像分割技术对立体图像进行预分割,得到分割区域内像素的聚合半径;以此半径为指导,在立体图代价空间中以3种不同尺寸的核进行滤波,引入正则化项确保聚合代价的一致性,以得到更有效的聚合代价;运用简单高效的贪心策略获取初步视差。基于Middlebury测试平台的实验结果表明所提算法兼具实时性和高效性。
To solve problems of the difficulty to meet the real-time requirements and the low matching accuracy of existing local stereo matching algorithms at some special regions,such as weak textured surfaces and the discontinuity boundary of depth,a dense stereo matching algorithm based on cross-scale guided image filtering is proposed.An image segmentation technology is used to realize pre-segmentation of stereo images and the aggregation radius of pixels in the segmented region is obtained.This radius is used as a guide,and kernels with three different sizes are used to carry out filtering in the cost space of stereo image.The regularization term is introduced to ensure the consistency of the aggregated cost,so as to obtain a more efficient aggregate cost.A simple and efficient winner-take-all strategy is used to obtain the initial disparity.The experimental results based on Middlebury test bench show that the proposed algorithm has both real time capability and high efficiency.
To solve problems of the difficulty to meet the real-time requirements and the low matching accuracy of existing local stereo matching algorithms at some special regions,such as weak textured surfaces and the discontinuity boundary of depth,a dense stereo matching algorithm based on cross-scale guided image filtering is proposed.An image segmentation technology is used to realize pre-segmentation of stereo images and the aggregation radius of pixels in the segmented region is obtained.This radius is used as a guide,and kernels with three different sizes are used to carry out filtering in the cost space of stereo image.The regularization term is introduced to ensure the consistency of the aggregated cost,so as to obtain a more efficient aggregate cost.A simple and efficient winner-take-all strategy is used to obtain the initial disparity.The experimental results based on Middlebury test bench show that the proposed algorithm has both real time capability and high efficiency.
引文
[1]Scharstein D,Szeliski R,Zabih R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[C].IEEE Stereo and Multi-Baseline Vision,2002,47(1):7-42.
[2]Bleyer M,Gelautz M.Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions[J].Signal Processing:Image Communication,2007,22(2):127-143.
[3]Kim J C,Lee K M,Choi B T.A dense stereo matching using two-pass dynamic programming with generalized ground control points[C].IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2005,2(2):1075-1082.
[4]Luo W J,Schwing A G,Urtasun R.Efficient deep learning for stereo matching[C].IEEE Conference on Computer Vision and Pattern Recognition,2016:5695-5703.
[5]bontar J,LeCun Y.Stereo matching by training a convolutional neural network to compare image patches[J].The Journal of Machine Learning Research,2016,17(1):2287-2318.
[6]Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window:Theory and experiment[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(9):920-932.
[7]Yoon K J,Kweon S.Adaptive support-weight approach for correspondence search[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2006,28(4):650-656.
[8]Shi H,Zhu H,Wang J,et al.Segment-based adaptive window and multi-feature fusion for stereo matching[J].Journal of Algorithms and Computational Technology,2016,10(1):184-200.
[9]Yang Q X.Stereo matching using tree filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(4):834-846.
[10]Rhemann C,Hosni A,Bleyer M,et al.Fast costvolume filtering for visual correspondence and beyond[C].IEEE Conference on Computer Vision and Pattern Recognition,2011:3017-3024.
[11]He K M,Sun J,Tang X O.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[12]Zhang K,Fang Y Q,Min D B,et al.Cross-scale cost aggregation for stereo matching[J].IEEEConference on Transactions on Circuits and Systems for Video Technology,2017,27(5):965-976.
[13]Zhu S P,Yan L N,Li Z.Stereo matching algorithm based on improved Census transform and dynamic programming[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.
[14]Crow F C.Summed-area tables for texture mapping[C].ACM Conference on Computer Graphics and Interactive Techniques,1984:207-212.
[15]Pires B R,Singh K,Moura J M F.Approximating image filters with box filters[C].IEEE International Conference on Image Processing,2011:85-88.
[16]Comaniciu D,Meer P.Mean shift:A robust approach toward feature space analysis[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[17]Liu J,Zhang J X,Dai Y.Dense stereo matching based on region growing[J].Robot,2017,39(2):182-188.刘杰,张建勋,代煜.基于区域增长的稠密立体匹配[J].机器人,2017,39(2):182-188.
[18]Milanfar P.A tour of modern image filtering:New insights and methods,both practical and theoretical[J].IEEE Signal Processing Magazine,2013,30(1):106-128.
[19]Scharstein D,Szeliski R,Hirschmüller H.The middlebury stereo vision page[EB/OL].http://vision.middlebury.edu/stereo/.
[20]Zhang K,Lu J B,Lafruit G.Cross-based local stereo matching using orthogonal integral images[J].IEEETransactions on Circuits and Systems for Video Technology,2009,19(7):1073-1079.
[21]Wang L,Yang R G.Global stereo matching leveraged by sparse ground control points[C].IEEEConference on Computer Vision and Pattern Recognition,2011:3033-3040.
[2]Bleyer M,Gelautz M.Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions[J].Signal Processing:Image Communication,2007,22(2):127-143.
[3]Kim J C,Lee K M,Choi B T.A dense stereo matching using two-pass dynamic programming with generalized ground control points[C].IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2005,2(2):1075-1082.
[4]Luo W J,Schwing A G,Urtasun R.Efficient deep learning for stereo matching[C].IEEE Conference on Computer Vision and Pattern Recognition,2016:5695-5703.
[5]bontar J,LeCun Y.Stereo matching by training a convolutional neural network to compare image patches[J].The Journal of Machine Learning Research,2016,17(1):2287-2318.
[6]Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window:Theory and experiment[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(9):920-932.
[7]Yoon K J,Kweon S.Adaptive support-weight approach for correspondence search[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2006,28(4):650-656.
[8]Shi H,Zhu H,Wang J,et al.Segment-based adaptive window and multi-feature fusion for stereo matching[J].Journal of Algorithms and Computational Technology,2016,10(1):184-200.
[9]Yang Q X.Stereo matching using tree filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(4):834-846.
[10]Rhemann C,Hosni A,Bleyer M,et al.Fast costvolume filtering for visual correspondence and beyond[C].IEEE Conference on Computer Vision and Pattern Recognition,2011:3017-3024.
[11]He K M,Sun J,Tang X O.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409.
[12]Zhang K,Fang Y Q,Min D B,et al.Cross-scale cost aggregation for stereo matching[J].IEEEConference on Transactions on Circuits and Systems for Video Technology,2017,27(5):965-976.
[13]Zhu S P,Yan L N,Li Z.Stereo matching algorithm based on improved Census transform and dynamic programming[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.
[14]Crow F C.Summed-area tables for texture mapping[C].ACM Conference on Computer Graphics and Interactive Techniques,1984:207-212.
[15]Pires B R,Singh K,Moura J M F.Approximating image filters with box filters[C].IEEE International Conference on Image Processing,2011:85-88.
[16]Comaniciu D,Meer P.Mean shift:A robust approach toward feature space analysis[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[17]Liu J,Zhang J X,Dai Y.Dense stereo matching based on region growing[J].Robot,2017,39(2):182-188.刘杰,张建勋,代煜.基于区域增长的稠密立体匹配[J].机器人,2017,39(2):182-188.
[18]Milanfar P.A tour of modern image filtering:New insights and methods,both practical and theoretical[J].IEEE Signal Processing Magazine,2013,30(1):106-128.
[19]Scharstein D,Szeliski R,Hirschmüller H.The middlebury stereo vision page[EB/OL].http://vision.middlebury.edu/stereo/.
[20]Zhang K,Lu J B,Lafruit G.Cross-based local stereo matching using orthogonal integral images[J].IEEETransactions on Circuits and Systems for Video Technology,2009,19(7):1073-1079.
[21]Wang L,Yang R G.Global stereo matching leveraged by sparse ground control points[C].IEEEConference on Computer Vision and Pattern Recognition,2011:3033-3040.