稀疏深度图匹配关键技术研究
|
摘要
三维数据的获取问题对于3DGIS而言具有极其重要的意义。基于摄影测量与多视几何理论的影像匹配技术可以获得地面高程信息、纹理数据等,它已逐渐成为三维数据获取的最主要手段之一。基于影像匹配所得的结果是稠密深度图,它包含了影像中每个象素的三维信息,但由此得到的三维数据用在3DGIS建模时需要进行大量简化,同时当影像中存在大范围非特征区域时,易产生大量的误匹配。为此,论文针对3DGIS建模的需求,研究了稀疏深度图匹配的关键技术,旨在快速自动生成特征区域内的深度图,回避对纹理稀疏区域的匹配。论文的主要工作有：
1)介绍了双目立体视觉成像原理以及基于多视几何理论的核线影像求解方法,分析了影像匹配中的约束条件、难点和匹配算法的主要评价手段。
2)提出了一种基于法向量的特征区域提取算法。该算法根据象素点邻域内法向量的变化程度来判断其是否为特征点,有效提取了灰度变化剧烈的区域,过滤了特征不明显的平滑区域。
3)对现有的影像匹配算法进行了对比、分析和总结。提出一种基于特征区域的稀疏深度图匹配算法。将影像看成是一个连续的三维曲面,以特征区域作为匹配对象,利用匹配窗口中对应法向量的余弦值之总和构造匹配代价函数。基于特征区域的匹配可以回避对纹理缺乏区域的错误匹配,同时加快了计算速度。
4)利用C++语言开发了上述算法,使用真实影像数据进行了匹配实验。结果表明,本文匹配算法可以有效地生成稀疏深度图,错误匹配率较低,并能满足3DGIS中的建模需求。
The 3D data acquisition is very important for 3D Geographic Information System (3DGIS). Image matching based on Photogrammetry and multiple view geometry has become one of the main means of 3D data acquisition which can obtain ground elevation and texture data. Dense depth map as the result of image matching contains 3D information of each image pixel. But the 3D data extracted from this way need to be simplified if used for 3D modeling in 3DGIS. On the other hand, if sparse texture regions exist in the images, it's difficult to overcome the error matches. Therefore, for the need of 3DGIS modeling, the author studies the key technologies of sparse depth map matching. The objective is to quickly generate sparse depth map automatically and avoid mismatching in texture-less regions.
The main work is as follows:
1) The imaging principle of binocular stereo vision, the basic theory and solution method of epipolar image generation are introduced. Then the image matching constraints, difficulties and evaluation means are analyzed.
2) The author proposes an extraction algorithm of feature regions based on normal vector. The method judges whether the pixel is feature point or not according to the change degree of normal vectors in pixel neighborhood. It effectively extracts the regions in which the gray scale changes greatly and filters the smooth areas with no remarkable feature.
3) After comparing and analyzing the matching algorithms in current reference, the author presents a sparse depth map matching algorithm based on feature regions. The algorithm takes one image as a continuous 3D surface, and mainly matches feature regions. The summary of cosine values of corresponding normal vectors in two match windows are adopted as the cost functions. The algorithm based on feature regions can filter sparse texture regions to avoid mismatch and save computer time.
4) C++ language is used to implement this algorithm, and the real image data is used for checking it. The results show that the proposed algorithm is effective to obtain the sparse depth maps which can satisfy 3DGIS modeling.
1)介绍了双目立体视觉成像原理以及基于多视几何理论的核线影像求解方法,分析了影像匹配中的约束条件、难点和匹配算法的主要评价手段。
2)提出了一种基于法向量的特征区域提取算法。该算法根据象素点邻域内法向量的变化程度来判断其是否为特征点,有效提取了灰度变化剧烈的区域,过滤了特征不明显的平滑区域。
3)对现有的影像匹配算法进行了对比、分析和总结。提出一种基于特征区域的稀疏深度图匹配算法。将影像看成是一个连续的三维曲面,以特征区域作为匹配对象,利用匹配窗口中对应法向量的余弦值之总和构造匹配代价函数。基于特征区域的匹配可以回避对纹理缺乏区域的错误匹配,同时加快了计算速度。
4)利用C++语言开发了上述算法,使用真实影像数据进行了匹配实验。结果表明,本文匹配算法可以有效地生成稀疏深度图,错误匹配率较低,并能满足3DGIS中的建模需求。
The 3D data acquisition is very important for 3D Geographic Information System (3DGIS). Image matching based on Photogrammetry and multiple view geometry has become one of the main means of 3D data acquisition which can obtain ground elevation and texture data. Dense depth map as the result of image matching contains 3D information of each image pixel. But the 3D data extracted from this way need to be simplified if used for 3D modeling in 3DGIS. On the other hand, if sparse texture regions exist in the images, it's difficult to overcome the error matches. Therefore, for the need of 3DGIS modeling, the author studies the key technologies of sparse depth map matching. The objective is to quickly generate sparse depth map automatically and avoid mismatching in texture-less regions.
The main work is as follows:
1) The imaging principle of binocular stereo vision, the basic theory and solution method of epipolar image generation are introduced. Then the image matching constraints, difficulties and evaluation means are analyzed.
2) The author proposes an extraction algorithm of feature regions based on normal vector. The method judges whether the pixel is feature point or not according to the change degree of normal vectors in pixel neighborhood. It effectively extracts the regions in which the gray scale changes greatly and filters the smooth areas with no remarkable feature.
3) After comparing and analyzing the matching algorithms in current reference, the author presents a sparse depth map matching algorithm based on feature regions. The algorithm takes one image as a continuous 3D surface, and mainly matches feature regions. The summary of cosine values of corresponding normal vectors in two match windows are adopted as the cost functions. The algorithm based on feature regions can filter sparse texture regions to avoid mismatch and save computer time.
4) C++ language is used to implement this algorithm, and the real image data is used for checking it. The results show that the proposed algorithm is effective to obtain the sparse depth maps which can satisfy 3DGIS modeling.
引文
[1]刘哲,严泰来,张晓东.3DGIS技术研究进展.中国农学通报,2006,22(11)：451-455
[2]朱庆.3维地理信息系统技术综述.地理信息世界,2004,2(3)：8-12
[3]隋婧,金伟其.双目立体视觉技术的实现及其进展.电子技术应用,2004,30(10)：4-6
[4]D.Marr. Vision, San Francisco:W.H. Freeman and Company,1982
[5]Barnard S.T, Fischler M. A Computational stereo ACM Computing Surveys 14, 1982.553-72
[6]S.M.Smith, J.M.Brady. SUSAN-a new approach to low level image processing. International Journal of Computer Vision,1997,23(1):45-75
[7]C.Harris, M.Stephens. A Combined Corner and edge Detector. Proceedings of the Alvey Vision Conference,1988.189-192
[8]H.P.Moravec. Visual Mapping by a Robot Rover. International Joint Conference on Artificial Intelligence,1979.598-600
[9]U.R.Dhond, J.K.Aggarwal. Structure from Stereo-A Review. IEEE Trans. SMC, 1989,19(6):1489-1510
[10]Faugeras O. What can be seen in three dimensions with an un-calibrated stereo rig[C]. Proc of the 2nd European Conf on Computer Vision. Santa Margherita Ligure,1992.563-578
[11]A.Koschan. What is New in Computational Stereo Since 1989:A Survey of Current Stereo Papers, Technical Report 93-22, Technical University of Berlin, 1993
[12]Hartley R, Zisserman A. Multiple View Geometry in Computer Vision. Cambridge, UK:Cambridge University Press,2000
[13]D.Scharstein, R.Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision,2002, 47(1/2/3):7-42
[141 http://vision.middleburv.edu/stereo/data/scenes2003/
[15]L.Wang, S.B.Kang, H.Y.Shum, et al, Cooperative segmentation and stereo using perspective space search, Asian Conf. on Computer Vision, Jeju Island, South Korea, Jan.2004, vol.1.366-371
[16]Kim H, Sohn K. Hierarchical disparity estimation with energy-based
regularization[C]. Proc of Int Conf on Image Processing. Barcelona,2003. 373-376
[17]徐奕,周军,周源华.基于小波及动态规划的相位匹配[J].上海交通大学学报,2003,37(3)：388-392
[18]Ohta Y, Kanade T. Stereo by intra-and inter-scanline search using dynamic programming[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,1985, 7(2):139-154
[19]Cox, Roy S. A maximum-flow formulation of the N-camera stereo correspondence problem[C]. Proc of the 6th Int Conf on Computer Vision. Bombay,1998.492-499
[20]Zitnick L C, Kanade T. A cooperative algorithm for stereo matching and occlusion detection[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2000, 22(7):675-681
[21]Sun J, Zheng N N, Shum H Y. Stereo matching using belief propagation [J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(7):787-800
[22]M.Sarkis, K.Diepold. Sparse Stereo Matching using Belief Propagation, in IEEE Int. Conf. Image Processing (ICIP), Oct.2008
[23]Klaus, M.Sormann, K.Karner. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. ICPR 2006
[24]Z.Wang and Z.Zheng. A region based stereo matching algorithm using cooperative optimization. CVPR 2008
[25]M.Bleyer, C.Rother, P.Kohli. Surface stereo with soft segmentation. CVPR 2010
[26]Anonymous. Stereo matching based on under-and over-segmentation with occlusion handling. Submitted to PAMI 2009
[27]Ma Y., Soatto S., et al. An Invitation to 3-D Vision:From Images to Geometric Models, Interdisciplinary Applied Mathematics, Springer, November 2003
[28]马颂德,张正友.计算机视觉-计算理论与算法基础.科学出版社,1998
[29]张祖勋,张剑清.数字摄影测量[M].武汉：武汉测绘科技大学出版社,1996
[30]韦穗,杨尚骏,章权兵等.计算机视觉中的多视图几何.安徽：安徽大学出版社,2002
[31]H. MORAVEC. Obstacle avoidance and navigation in the real world by a seeing robot rover. PhD thesis, Stanford Univ., Sept.1980
[32]W. Forstner, E. Gulch. A Fast Operator for Detection and Precise Location of Distinct Points, Corners, and Circular Features, in Proc. of ISPRS Inter-commission Workshop, Interlaken, Switzerland,1987
[33]JAIN A K. A fast Karhunen-Loeve transform for a class of random processes [J]. IEEE Trans,1976,24(9):1023-1029
[34]魏士俨.地面立体影像匹配技术研究：[硕士论文].北京：北京建筑工程学院,2008,11-12
[35]Fischler M A, Bolles R C. Random sample consensus:A paradigm for model fitting with applications to image analysis and automated cartography [J]. communications ACM,1981,24(6):381-395
[36]孙敏,胡争.基于多视几何理论的超低空摄影测量数据处理方法.测绘科学前沿技术论坛,南京,2008
[37]Koch R. Surface Reconstruction from Stereoscopic Image Sequences, ICCV95, 1995.109-113
[38]钱曾波,邱振戈,张永强.计算机立体视觉研究的进展.测绘学院学报,2001,18(4)：267-272
[39]周秀芝.面向深度提取和形状识别的图像匹配.[博士论文].长沙：国防科学技术大学,2006,20-21
[40]徐奕,周军,周华源.立体匹配技术[J].计算机工程与应用,2003,39(15)：1-5
[41]Brown Lisa G. A Survey of Image Registration Techniques [J]. ACM Computing Surveys,1992,24 (4):325-376
[42]O.Veksler. Fast variable window for stereo correspondence using integral images. In CVPR,2003.1:556-561
[43]Zeng Z.G., H.Yan. Region matching and optimal matching pair theorem in International Computer Graphics,2001
[44]R.Zabih, J.Woodfill. Non-Parametric Local Transforms for Computing Visual Correspondence. In Proceeding of the Third European Conference Computer Vision.1994. Stockholm Sweden, vol.2:151-158
[45]K.J.Yoon, I.S.Kweon. Adaptive Support-Weight Approach for Correspondence Search. IEEE Trans. PAMI,2006,28(4):650-656
[46]T.Kanade, M.Okutomi. A stereo matching algorithm with an adaptive window: Theory and experiment. IEEE Trans. PAMI,1994,16(9):920-932
[47]D.Rosenholm. Multi-point matching using the least-squares technique for an evaluation of three-dimensional models. Photogrammatic Engineering and Remote Sensing,1987,53(6):1214-1218
[48]O.Veksler. Stereo matching by compact windows via minimum ratio cycle. In Proceeding ICCVV.2001. vol.1:540-547
[49]Y.Wei, L.Quan. Region-Based Progressive Stereo Matching. In CVPR.2004,1: 106-113
[50]M.Bleyer, M.Gelautz. A Layered Stereo Algorithm Using Image Segmentation and Global Visibility Constraints. In IEEE International Conference on Image Processing,2004.2997-3000
[51]Andreas Klaus, Mario Sormann, Konrad Karner. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure[C]. IEEE International Conference on Pattern Recognition,2006.15-18
[52]F.Tombari, S.Mattoccia, L.D.Stefano. Segmentation based adaptive support for accurate stereo correspondence. In PSIVT,2007.427-438
[53]Wang Zengfu, Zheng Zhigang. A region based stereo matching algorithm using cooperative optimization[C]. IEEE International Conference on Computer Vision and Pattern Recognition,2008.887-894
[54]刘天亮,罗立民.一种基于分割的可变权值和视差估计的立体匹配算法.光学学报,2009(4)：1002-1009
[55]白明,庄严,王伟.双目立体匹配算法的研究与进展.控制与决策,2008,23(7)：721-729
[56]徐奕,周军.周源华基于动态规划的相位匹配和遮挡检测. 电子学报,2004,32(4)：591-595
[57]徐彦君,金贵昌.基于相位的尺度自适应立体匹配方法.电子学报,1999,27(7)：38-41
[58]Bobick A F, Intille S S. Large occlusion sereo[J]. Int J of Computer Vision,1999, 33(3):181-200
[59]Birchfield, Tomasi. Depth discontinuities by pixel-to-pixel stereo[J]. International Journal of Computer Vision,1999,35(3):269-293
[60]Lei C, Seizer J, Yang Y H. Region-tree based stereo using dynamic programming optimization[C]. Proc of IEEE Conf on Computer Vision and Pattern Recognition. New York,2006,378-385
[61]Y.Boykov, O.Veksler, R.Zabih. Fast approximate energy minimization via graph cuts. IEEE Trans. PAMI,2001,23(11):1222-1239
[62]Kolmogorov V, Zabin R. What energy functions can be minimized via graph cuts?[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2004,26(2): 147-159
[63]Y.Boykov, V.Kolmogorov. An Experimental Comparison of Min-Cut/Max-Flow
Algorithms for Energy Minimization in Vision, IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1124-1137
[64]Y.Ruichek. Multilevel and neural network based stereo matching method for real-time obstacle detection using linear cameras[J]. IEEE Trans on Intelligent Transportation Systems,2005,6(1):154-162
[65]Hua X J, Yokomichi M, Kono M. Stereo correspondence using color based on competitive cooperative neural networks [C]. Proc of the 6th Int Conf on Parallel and Distributed Computing, Applications and Technologies.2005.856-860
[66]Ruichek Y, Issa H, Postaire J G, et al. Towards real-time obstacle detection using a hierarchical decomposition methodology for stereo matching with a genetic algorithm[C]. Proc of the 16th IEEE Int Conf on Tools with Artificial Intelligence. Boca Raton,2004.138-147
[67]D. Scharstein, R. Szeliski. Stereo matching with nonlinear diffusion. International Journal of Computer Vision,1998,28(2):155-174
[68]李鸣翔,贾云得.基于自适应聚合的立体视觉合作算法.软件学报,2008,19(7)：1674-1682
[69]P Felzeneszwalb, D Hutenlocher. Efficient Belief Propagation for Early Vision[J]. International Journal of Computer Vision,2006,70(1):41-54
[70]J. Shah. A Nonlinear Diffusion Model for Discontinuous Disparity and Half-Occlusions in Stereo. In CVPR.1993,34-40
[71]C.Tomasi, R.Manduchi. Stereo Matching as a Nearest-Neighbor Problem. IEEE Trans. PAMI,1998,20:333-340
[72]C.Tomasi, R.Manduchi. Stereo without Search. ECCV, Cambridge, UK,1996, 452-465
[73]张力,张祖勋,张剑清.Wallis滤波在影像匹配中的应用.武汉测绘科技大学学报,1993,24(1)：24-27
[74]D.Gordan, R.Reynolds. Image Space Shading of 3D Object, CVGIP, Vol.29,1985
[75]石教英,蔡文立,科学计算可视化算法与系统.科学出版社,1996
[76]K.Hohne, R.Bernstein. Shading 3D Image from CT Using Gray Level Gradients, IEEE Trans. on Medical Imaging,5(1),1986
[77]周启鸣,刘学军.数字地形分析.科学出版社,2006.91
[2]朱庆.3维地理信息系统技术综述.地理信息世界,2004,2(3)：8-12
[3]隋婧,金伟其.双目立体视觉技术的实现及其进展.电子技术应用,2004,30(10)：4-6
[4]D.Marr. Vision, San Francisco:W.H. Freeman and Company,1982
[5]Barnard S.T, Fischler M. A Computational stereo ACM Computing Surveys 14, 1982.553-72
[6]S.M.Smith, J.M.Brady. SUSAN-a new approach to low level image processing. International Journal of Computer Vision,1997,23(1):45-75
[7]C.Harris, M.Stephens. A Combined Corner and edge Detector. Proceedings of the Alvey Vision Conference,1988.189-192
[8]H.P.Moravec. Visual Mapping by a Robot Rover. International Joint Conference on Artificial Intelligence,1979.598-600
[9]U.R.Dhond, J.K.Aggarwal. Structure from Stereo-A Review. IEEE Trans. SMC, 1989,19(6):1489-1510
[10]Faugeras O. What can be seen in three dimensions with an un-calibrated stereo rig[C]. Proc of the 2nd European Conf on Computer Vision. Santa Margherita Ligure,1992.563-578
[11]A.Koschan. What is New in Computational Stereo Since 1989:A Survey of Current Stereo Papers, Technical Report 93-22, Technical University of Berlin, 1993
[12]Hartley R, Zisserman A. Multiple View Geometry in Computer Vision. Cambridge, UK:Cambridge University Press,2000
[13]D.Scharstein, R.Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision,2002, 47(1/2/3):7-42
[141 http://vision.middleburv.edu/stereo/data/scenes2003/
[15]L.Wang, S.B.Kang, H.Y.Shum, et al, Cooperative segmentation and stereo using perspective space search, Asian Conf. on Computer Vision, Jeju Island, South Korea, Jan.2004, vol.1.366-371
[16]Kim H, Sohn K. Hierarchical disparity estimation with energy-based
regularization[C]. Proc of Int Conf on Image Processing. Barcelona,2003. 373-376
[17]徐奕,周军,周源华.基于小波及动态规划的相位匹配[J].上海交通大学学报,2003,37(3)：388-392
[18]Ohta Y, Kanade T. Stereo by intra-and inter-scanline search using dynamic programming[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,1985, 7(2):139-154
[19]Cox, Roy S. A maximum-flow formulation of the N-camera stereo correspondence problem[C]. Proc of the 6th Int Conf on Computer Vision. Bombay,1998.492-499
[20]Zitnick L C, Kanade T. A cooperative algorithm for stereo matching and occlusion detection[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2000, 22(7):675-681
[21]Sun J, Zheng N N, Shum H Y. Stereo matching using belief propagation [J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(7):787-800
[22]M.Sarkis, K.Diepold. Sparse Stereo Matching using Belief Propagation, in IEEE Int. Conf. Image Processing (ICIP), Oct.2008
[23]Klaus, M.Sormann, K.Karner. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. ICPR 2006
[24]Z.Wang and Z.Zheng. A region based stereo matching algorithm using cooperative optimization. CVPR 2008
[25]M.Bleyer, C.Rother, P.Kohli. Surface stereo with soft segmentation. CVPR 2010
[26]Anonymous. Stereo matching based on under-and over-segmentation with occlusion handling. Submitted to PAMI 2009
[27]Ma Y., Soatto S., et al. An Invitation to 3-D Vision:From Images to Geometric Models, Interdisciplinary Applied Mathematics, Springer, November 2003
[28]马颂德,张正友.计算机视觉-计算理论与算法基础.科学出版社,1998
[29]张祖勋,张剑清.数字摄影测量[M].武汉：武汉测绘科技大学出版社,1996
[30]韦穗,杨尚骏,章权兵等.计算机视觉中的多视图几何.安徽：安徽大学出版社,2002
[31]H. MORAVEC. Obstacle avoidance and navigation in the real world by a seeing robot rover. PhD thesis, Stanford Univ., Sept.1980
[32]W. Forstner, E. Gulch. A Fast Operator for Detection and Precise Location of Distinct Points, Corners, and Circular Features, in Proc. of ISPRS Inter-commission Workshop, Interlaken, Switzerland,1987
[33]JAIN A K. A fast Karhunen-Loeve transform for a class of random processes [J]. IEEE Trans,1976,24(9):1023-1029
[34]魏士俨.地面立体影像匹配技术研究：[硕士论文].北京：北京建筑工程学院,2008,11-12
[35]Fischler M A, Bolles R C. Random sample consensus:A paradigm for model fitting with applications to image analysis and automated cartography [J]. communications ACM,1981,24(6):381-395
[36]孙敏,胡争.基于多视几何理论的超低空摄影测量数据处理方法.测绘科学前沿技术论坛,南京,2008
[37]Koch R. Surface Reconstruction from Stereoscopic Image Sequences, ICCV95, 1995.109-113
[38]钱曾波,邱振戈,张永强.计算机立体视觉研究的进展.测绘学院学报,2001,18(4)：267-272
[39]周秀芝.面向深度提取和形状识别的图像匹配.[博士论文].长沙：国防科学技术大学,2006,20-21
[40]徐奕,周军,周华源.立体匹配技术[J].计算机工程与应用,2003,39(15)：1-5
[41]Brown Lisa G. A Survey of Image Registration Techniques [J]. ACM Computing Surveys,1992,24 (4):325-376
[42]O.Veksler. Fast variable window for stereo correspondence using integral images. In CVPR,2003.1:556-561
[43]Zeng Z.G., H.Yan. Region matching and optimal matching pair theorem in International Computer Graphics,2001
[44]R.Zabih, J.Woodfill. Non-Parametric Local Transforms for Computing Visual Correspondence. In Proceeding of the Third European Conference Computer Vision.1994. Stockholm Sweden, vol.2:151-158
[45]K.J.Yoon, I.S.Kweon. Adaptive Support-Weight Approach for Correspondence Search. IEEE Trans. PAMI,2006,28(4):650-656
[46]T.Kanade, M.Okutomi. A stereo matching algorithm with an adaptive window: Theory and experiment. IEEE Trans. PAMI,1994,16(9):920-932
[47]D.Rosenholm. Multi-point matching using the least-squares technique for an evaluation of three-dimensional models. Photogrammatic Engineering and Remote Sensing,1987,53(6):1214-1218
[48]O.Veksler. Stereo matching by compact windows via minimum ratio cycle. In Proceeding ICCVV.2001. vol.1:540-547
[49]Y.Wei, L.Quan. Region-Based Progressive Stereo Matching. In CVPR.2004,1: 106-113
[50]M.Bleyer, M.Gelautz. A Layered Stereo Algorithm Using Image Segmentation and Global Visibility Constraints. In IEEE International Conference on Image Processing,2004.2997-3000
[51]Andreas Klaus, Mario Sormann, Konrad Karner. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure[C]. IEEE International Conference on Pattern Recognition,2006.15-18
[52]F.Tombari, S.Mattoccia, L.D.Stefano. Segmentation based adaptive support for accurate stereo correspondence. In PSIVT,2007.427-438
[53]Wang Zengfu, Zheng Zhigang. A region based stereo matching algorithm using cooperative optimization[C]. IEEE International Conference on Computer Vision and Pattern Recognition,2008.887-894
[54]刘天亮,罗立民.一种基于分割的可变权值和视差估计的立体匹配算法.光学学报,2009(4)：1002-1009
[55]白明,庄严,王伟.双目立体匹配算法的研究与进展.控制与决策,2008,23(7)：721-729
[56]徐奕,周军.周源华基于动态规划的相位匹配和遮挡检测. 电子学报,2004,32(4)：591-595
[57]徐彦君,金贵昌.基于相位的尺度自适应立体匹配方法.电子学报,1999,27(7)：38-41
[58]Bobick A F, Intille S S. Large occlusion sereo[J]. Int J of Computer Vision,1999, 33(3):181-200
[59]Birchfield, Tomasi. Depth discontinuities by pixel-to-pixel stereo[J]. International Journal of Computer Vision,1999,35(3):269-293
[60]Lei C, Seizer J, Yang Y H. Region-tree based stereo using dynamic programming optimization[C]. Proc of IEEE Conf on Computer Vision and Pattern Recognition. New York,2006,378-385
[61]Y.Boykov, O.Veksler, R.Zabih. Fast approximate energy minimization via graph cuts. IEEE Trans. PAMI,2001,23(11):1222-1239
[62]Kolmogorov V, Zabin R. What energy functions can be minimized via graph cuts?[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2004,26(2): 147-159
[63]Y.Boykov, V.Kolmogorov. An Experimental Comparison of Min-Cut/Max-Flow
Algorithms for Energy Minimization in Vision, IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1124-1137
[64]Y.Ruichek. Multilevel and neural network based stereo matching method for real-time obstacle detection using linear cameras[J]. IEEE Trans on Intelligent Transportation Systems,2005,6(1):154-162
[65]Hua X J, Yokomichi M, Kono M. Stereo correspondence using color based on competitive cooperative neural networks [C]. Proc of the 6th Int Conf on Parallel and Distributed Computing, Applications and Technologies.2005.856-860
[66]Ruichek Y, Issa H, Postaire J G, et al. Towards real-time obstacle detection using a hierarchical decomposition methodology for stereo matching with a genetic algorithm[C]. Proc of the 16th IEEE Int Conf on Tools with Artificial Intelligence. Boca Raton,2004.138-147
[67]D. Scharstein, R. Szeliski. Stereo matching with nonlinear diffusion. International Journal of Computer Vision,1998,28(2):155-174
[68]李鸣翔,贾云得.基于自适应聚合的立体视觉合作算法.软件学报,2008,19(7)：1674-1682
[69]P Felzeneszwalb, D Hutenlocher. Efficient Belief Propagation for Early Vision[J]. International Journal of Computer Vision,2006,70(1):41-54
[70]J. Shah. A Nonlinear Diffusion Model for Discontinuous Disparity and Half-Occlusions in Stereo. In CVPR.1993,34-40
[71]C.Tomasi, R.Manduchi. Stereo Matching as a Nearest-Neighbor Problem. IEEE Trans. PAMI,1998,20:333-340
[72]C.Tomasi, R.Manduchi. Stereo without Search. ECCV, Cambridge, UK,1996, 452-465
[73]张力,张祖勋,张剑清.Wallis滤波在影像匹配中的应用.武汉测绘科技大学学报,1993,24(1)：24-27
[74]D.Gordan, R.Reynolds. Image Space Shading of 3D Object, CVGIP, Vol.29,1985
[75]石教英,蔡文立,科学计算可视化算法与系统.科学出版社,1996
[76]K.Hohne, R.Bernstein. Shading 3D Image from CT Using Gray Level Gradients, IEEE Trans. on Medical Imaging,5(1),1986
[77]周启鸣,刘学军.数字地形分析.科学出版社,2006.91