3D字幕技术研究
|
摘要
随着科技的进步和大众对生活品质的不断追求，记录真实三维世界的立体电影备受瞩目。三维电影给观众带来了前所未有的视觉冲击和丰盛的视觉享受，但同时也引发了新的问题——视觉疲劳。3D字幕对立体图像内容的干扰是一个主要原因。本文的研究目标是实现一个简单、便捷、观看舒适的3D字幕叠加系统。
作者在认真分析和总结了国内外的3D字幕技术的研究成果基础上，以双目立体视觉技术为理论依据，全面分析人眼的立体视觉特性，重点剖析双目视觉和焦点调节与会聚两个影响因素，实现了一个基于双目视觉的3D字幕叠加的系统。该系统主要依据立体图像对的双目视差信息，采用OpenGL中文汉字将具有视差的字幕叠加在立体图像对上。根据人类的心理立体视觉因素将字幕区域选定在图像底部，同时字幕的属性也随图像内容自适应调整。针对3D字幕视差的计算，本文采用改进的基于线增长的立体匹配算法获取稠密视差图。改进措施有采用Harris法选取种子点，松弛迭代方法剔除误匹配，以保证种子点选取的高精度；用中值滤波消除匹配后的噪声，使视差平滑过渡，获得了较为理想的视差效果图。
最终本文实现了基于立体图像内容的视差叠加3D字幕的系统，将叠加了3D字幕的立体图像对立体显示。实验结果表明，该3D字幕叠加系统可作为质量评价的测试平台，根据立体图像视差简单便捷的调整3D字幕的视差、属性等信息，以便达到同步舒适地观看立体图像和3D字幕的目的。
With the technology development and increasing demand of high quality life, thestereoscopic film, which can capture the real information of the world has attractedheavy attention from the community. The stereoscopic content provides the illusion ofdepth perception and visually stimulating to the viewer, but a new problem imposedby stereoscopic film is eye strain. One key factor is the display of 3D subtitle onstereoscopic image content. The purpose of this paper is to realize a simple,convenient system for overlaying stereoscopic subtitles, thus viewers are able towatch the stereo images and read subtitles mutually with ease and comfort.
The research of 3D subtitle technology home and abroad has been carefullystudied and summarized. After analysis of the binocular stereo vision and humanvisual feature, especially, the key influence factors------binocular disparity andconvergence & focus, the paper proposes that the main criteria for overlayingstereoscopic subtitles is the depth of stereoscopic image content. The system is basedon the principle of binocular disparity to overlay three-dimension subtitles by usingthe corresponding relation of 3D subtitles disparity and depth of field. The subtitlesare superimposed at the bottom of the image in terms of the human psychologicalstereo perceive. At the same time, the font attributes of subtitles changes adaptivelybased on the depth placement of image content. For the binocular disparitycomputation of stereoscopic subtitles, an improved dense stereo matching algorithmbased on line-growth is adopted. In order to guarantee the accuracy of the seeds, weadopt Harris corners detection to extract the seeds, and using relaxative iterationmethod to reduce the false match. Finally, we use median filter to eliminate imagenoise and unreliable disparity, thus obtaining clear disparity graph.
In conclusion, a system for overlaying stereoscopic subtitles has beenimplemented based on the depth of stereoscopic image content. The experimentsshow that the system for overlaying stereoscopic subtitles, as a quality estimation testplatform, can adjust the disparity and attributes of subtitles conveniently, and enableviewers to read the stereo images and subtitles with ease and comfort.
作者在认真分析和总结了国内外的3D字幕技术的研究成果基础上，以双目立体视觉技术为理论依据，全面分析人眼的立体视觉特性，重点剖析双目视觉和焦点调节与会聚两个影响因素，实现了一个基于双目视觉的3D字幕叠加的系统。该系统主要依据立体图像对的双目视差信息，采用OpenGL中文汉字将具有视差的字幕叠加在立体图像对上。根据人类的心理立体视觉因素将字幕区域选定在图像底部，同时字幕的属性也随图像内容自适应调整。针对3D字幕视差的计算，本文采用改进的基于线增长的立体匹配算法获取稠密视差图。改进措施有采用Harris法选取种子点，松弛迭代方法剔除误匹配，以保证种子点选取的高精度；用中值滤波消除匹配后的噪声，使视差平滑过渡，获得了较为理想的视差效果图。
最终本文实现了基于立体图像内容的视差叠加3D字幕的系统，将叠加了3D字幕的立体图像对立体显示。实验结果表明，该3D字幕叠加系统可作为质量评价的测试平台，根据立体图像视差简单便捷的调整3D字幕的视差、属性等信息，以便达到同步舒适地观看立体图像和3D字幕的目的。
With the technology development and increasing demand of high quality life, thestereoscopic film, which can capture the real information of the world has attractedheavy attention from the community. The stereoscopic content provides the illusion ofdepth perception and visually stimulating to the viewer, but a new problem imposedby stereoscopic film is eye strain. One key factor is the display of 3D subtitle onstereoscopic image content. The purpose of this paper is to realize a simple,convenient system for overlaying stereoscopic subtitles, thus viewers are able towatch the stereo images and read subtitles mutually with ease and comfort.
The research of 3D subtitle technology home and abroad has been carefullystudied and summarized. After analysis of the binocular stereo vision and humanvisual feature, especially, the key influence factors------binocular disparity andconvergence & focus, the paper proposes that the main criteria for overlayingstereoscopic subtitles is the depth of stereoscopic image content. The system is basedon the principle of binocular disparity to overlay three-dimension subtitles by usingthe corresponding relation of 3D subtitles disparity and depth of field. The subtitlesare superimposed at the bottom of the image in terms of the human psychologicalstereo perceive. At the same time, the font attributes of subtitles changes adaptivelybased on the depth placement of image content. For the binocular disparitycomputation of stereoscopic subtitles, an improved dense stereo matching algorithmbased on line-growth is adopted. In order to guarantee the accuracy of the seeds, weadopt Harris corners detection to extract the seeds, and using relaxative iterationmethod to reduce the false match. Finally, we use median filter to eliminate imagenoise and unreliable disparity, thus obtaining clear disparity graph.
In conclusion, a system for overlaying stereoscopic subtitles has beenimplemented based on the depth of stereoscopic image content. The experimentsshow that the system for overlaying stereoscopic subtitles, as a quality estimation testplatform, can adjust the disparity and attributes of subtitles conveniently, and enableviewers to read the stereo images and subtitles with ease and comfort.
引文
[1] BERIC Todor, Methods And Systems For Presenting Three DimensionalMotion Pictures With Content Adaptive Information, US, WO2010064118,2010-6-10
[2] Claydon,Laurence James (Buckinghamshire, GB),Systems, apparatus andmethods for subtitling for stereoscopic content,US,2010/0220175,2010-09-02
[3]清华大学，一种立体视频字幕添加方法及装置，中国专利20101028773.7，2012-07-09
[4]沈涵，立体电影研究：[硕士毕业论文]，上海；上海师范大学，2011
[5]荆其诚，人类的视觉，北京：科学出版社，1987（5），124~126
[6]文江涛，光栅式立体显示器重影问题的研究：[硕士毕业论文]，合肥；合肥工业大学，2007
[7]杨延宁，立体电视技术进展，中国有线电视，2004（21）：23~25
[8]杨嘉琛，立体图像客观质量评价与压缩技术研究：[博士毕业论文]，天津；天津大学，2008
[9]包化宇，观看立体影像引起的视觉疲劳与改进措施：[硕士毕业论文]，北京；北京邮电大学，2009
[10]侯春萍，一种平面图像立体化的新方法，电子学报，2002：1861~1864
[11] Julesz B.Binocular depth perception of computer generated pattens,BellSystem Technical Journal,1960,39(5):1125~1162
[12]张广军，机器视觉，北京：科学出版社，2005，37~39
[13]王琼华，三维立体显示综述，计算机应用，2010（3），579~581
[14]岳晓军，计算机三维视景立体显示技术研究：[硕士毕业论文]，陕西；西北工业大学，2006
[15]刘运周，观看立体图像时视觉疲劳的研究及改进措施：[硕士毕业论文]，北京；北京邮电大学，2010
[16]王爱红，王琼华，光栅式自由立体显示器概述，现代显示，2009(105)：14~17
[17]马颂德，张正友，计算机视觉——计算理论和算法基础，北京：科学出版，1998，2~6
[18]王忠波，立体视觉中匹配技术的研究：[硕士毕业论文]，大连；大连理工大学，2008
[19] Roberts L G,Machine Perception of three-dimensional solids,Cambridge:MIT Press,1965,159~197
[20] Marr, Vision, W.H. Freeman and Company,1982,46~48
[21] D Beymer, K Konolige. Real-time tracking of multiple people usingcontinuous detection,Proceedings of Intermational Conference on computer Vision,1999
[22] Minoru Asada,Takamaro Tanaka, Visual Tracking Of Unkown MovingObject By Adaptive Binocular Visual Servonig, Proceedings of IntermationalConference on Multisensor Fusion and Intelligent Systems, 1999
[23]张春秀，基于双目视觉的三维重建：[硕士毕业论文]，天津；天津大学，2010
[24]章毓晋，图像工程，北京：清华大学出版社，2007，105~107
[25] S.T. Barnard, M.A. Fischler. Computational Stereo. ACM ComputingSurveys, 1982(4): 553-572
[26] U.R.Dhond and J.K.Aggarwal, Structure from stereo-A Review,IEEETransactions on Systems. Man. and Cybernetics,1989, 19 (6):1489~1510
[27] Koschan, A.What is New in Computational Stereo Since 1989:A Survey ofCurrent Stereo Papers, Technical Report93-22, Univ. of Berlin, 1993
[28] Myron Z.Brown, D.Burschka and G D Halter. Advances in ComputationalStereo.TPAMI, 2005,25 (8)
[29] Scharstein D and Szeliski R. A taxonomy and evaluation of dense two-framestereo correspondence algorithms. International Journal of Computer Vision, 2002,47:7-42
[30] C. Harris, M. Stephens, A combined corner and edge detector, Proceedingsof the Alvey vision Conference, 1988, 189~192
[31] S.M.Smith, J.M.Brady, SUSAN-a new approach to low level imageprocessing. International Journal of Computer Vision, 1997, 23(11): 45~78
[32] Trajkovic,M and Hedley M,“Fast corner detection”,Image and Visioncomputing, Vol18, 1998,75:87
[33]尹世明，立体匹配中的若干问题研究，[硕士毕业论文]，长沙；国防科学技术大学，2006
[34] Z. G Zeng, H.Yan. Region matching and optimal matching pairtheorem,Computer Graphics International, 2001
[35]徐奕，周军，周源华，立体视觉匹配技术，计算机工程与应用，2003，39（15）：1~5
[36] T. Kanade and M.Okutomi, A Stereo Matching Algorithm with An adaptiveWindow: Theory and Experiment, IEEE Transactions on Pattern Analysis andMachine Intelligence, 1994, 16(9), 920~932
[37] Hirschmuller, H.,P.Innocent and J.Garibaldi, Real-Time Correlation-BasedStereo Vision with Reduced Border Errors. International Journal of Computer Vision,2002, 47, 550~580
[38] D. Rosenholm, Multi-point matching using the least-squares technique for anevaluation of three-dimensional models.Photogrammatic Engineering and RemoteSensing,1987,53(6): 1214~1218
[39] Veksler,O. Fast Variable Window for Stereo Correspondence Using IntegralImages, IEEE Conference on Computer Vision and Pattern Recognition, 2003, 1,556~561
[40] Yoon,K.-J. and I.-S.Kweon, Adaptive Support-Weight Approach forCorrespondence Search, IEEE Transactions on Pattern Analysis and MachineIntelligence, 2006, 28(4), 650~656
[41]周秀芝，文贡坚，王润生，自适应窗口快速立体匹配，计算机学报，2006，29（3）：473~479
[42] Zitnick,C.L.and T.Kanade, A Cooperative Algorithm for Stereo Matchingand Occlusion Detection, IEEE Transactions on Pattern Analysis and MachineIntelligence, 2000, 22(7), 675~684
[43] Zitnick C. L., Kanade T., A Cooperative Algorithm for Stereo Matching andOcclusion Detection, CMU Technical Report CMU-RI-TR-99-35, 1999
[44] S. A. Lloyd, E. R. Haddow and J. F. Boyce, A Parallel Binocular StereoAlgorithm Utilizing Dynamic Programming and Relaxation Labeling, ComputerVision, Graphics and Image Processing, 1987, 39, 202~225
[45] Kim C. A dense stereo matching generalized ground control points. usingtwo-pass dynamic programming with In CVPR, 2005, vo1.2: 1075~1082
[46] Roy S.,Cox I. J., A Maximum-Flow 'Formulation of the N-camera StereoCorrespondence Problem, IEEE Proceedings of International Conference onComputer lesion, Bombai, January, 1998:492~499
[47] Bleyer M,Gelautz M. A layered stereo algorithm using image segmentationand global visibility constraints, ISPRS Journal of Photogrammetry and RemoteSensing, 2005, 59 (3) :128~150
[48] Bleyer M,Gelautz M. Graph-cut-based stereo matching using imagesegmentation with symmetrical treat ment of occlusions.Signal Processing:ImageCommunication, 2007, 22 (2) :127~143
[49] V. Kolmogorov and R.Zabih, Computing Visual Correspondence WithOcclusions Using Graph Cuts, International Conference on Computer Vision, 2001,2:508~515
[50] Hong L. and G.Chen, Segment-based Stereo Matching Using Graph Cuts,IEEE Conference on Computer Vision and Pattern Recognition,2004, 1, 74~81
[51] Lhuillier M.,Quan L. Quasi-dense reconstruction from image sequence.In:7th European Conference on Computer Vision,COPENHAGEN ,2002,125~139
[52] Maxime Lhuillier, Long Quan, Robust Dense Matching using Local andGlobal Geometric Constraints. Proceedings of the 15th International Conference onPattern Recognition, Barcelona,Spain, 2000, vol.l:968~972
[53] Z. Megyesi, G. Kos, D. Chetverikov, Dense 3D reconstruction from imagesby normal aided matching. Machine Graphics&Vision International Journal, 15(1):3~28, 2006
[54] M.Habbecke, L. Kobbelt, A Surface-Growing Approach to Multi-ViewStereo Reconstruction.2007
[55]唐丽，基于区域增长的立体像对稠密匹配算法，计算机报，2004，(27)：936~943
[56]刘战杰等，一种新的基于区域生长的彩色图像分割算法，山东大学学报（理学报），2010，145（7）：76~80
[57]唐丽，由手提相机获得的序列图像进行三维重建：[博士毕业论文]，西安；西安电子科技大学，2003
[58] B. B. Alagoz, Obtaining Depth Maps From Color Images By Region BasedStereo Matching Algorithms, OncuBilim Algorithm And Systems Labs. Vol.08,Art.No:04,2008
[59]孟晶晶，基于区域增长的立体匹配算法研究：[硕士毕业论文]，大连；大连理工大学2006
[60] Moravec H.P, Towards automatic visual obstacle avoidance, In 5thInternational Joint Conference on Artificial Intelligence, 1977: 584
[61] Z. Zhang, R.Deriche, O.Faugeras and Q.T.Luong, A robust technique formatching two uncalibrated images through the recovery of Unknown epipolarGeometry, Artificial Intelligence, 1995, 78(1-2): 87~119
[62]徐明亮，卢红星，王琬，OpenGL游戏编程，北京：机械工业社，2008：126~132
[63]安平，立体图像分层交叠块视差估计与自适应补偿，通信学报，2003，24 (3)：1~7
[64] Fua. A parallel stereo algorithm that produces dense depth maps andpreserves image features ,1993
[65] Knight's Quest 3D[EB/OL], http:// www.nvidia.cn/ object/3d-vision-3dmovies-cn.html
[66] Sizzle 3D Stereoscopic Video with Proper 3D Subtitles Overlayed[EB/OL],http://3dvision-blog.com/sizzle-3d-stereoscopic-video-with-proper-3d-subtitles-overlayed/
[2] Claydon,Laurence James (Buckinghamshire, GB),Systems, apparatus andmethods for subtitling for stereoscopic content,US,2010/0220175,2010-09-02
[3]清华大学，一种立体视频字幕添加方法及装置，中国专利20101028773.7，2012-07-09
[4]沈涵，立体电影研究：[硕士毕业论文]，上海；上海师范大学，2011
[5]荆其诚，人类的视觉，北京：科学出版社，1987（5），124~126
[6]文江涛，光栅式立体显示器重影问题的研究：[硕士毕业论文]，合肥；合肥工业大学，2007
[7]杨延宁，立体电视技术进展，中国有线电视，2004（21）：23~25
[8]杨嘉琛，立体图像客观质量评价与压缩技术研究：[博士毕业论文]，天津；天津大学，2008
[9]包化宇，观看立体影像引起的视觉疲劳与改进措施：[硕士毕业论文]，北京；北京邮电大学，2009
[10]侯春萍，一种平面图像立体化的新方法，电子学报，2002：1861~1864
[11] Julesz B.Binocular depth perception of computer generated pattens,BellSystem Technical Journal,1960,39(5):1125~1162
[12]张广军，机器视觉，北京：科学出版社，2005，37~39
[13]王琼华，三维立体显示综述，计算机应用，2010（3），579~581
[14]岳晓军，计算机三维视景立体显示技术研究：[硕士毕业论文]，陕西；西北工业大学，2006
[15]刘运周，观看立体图像时视觉疲劳的研究及改进措施：[硕士毕业论文]，北京；北京邮电大学，2010
[16]王爱红，王琼华，光栅式自由立体显示器概述，现代显示，2009(105)：14~17
[17]马颂德，张正友，计算机视觉——计算理论和算法基础，北京：科学出版，1998，2~6
[18]王忠波，立体视觉中匹配技术的研究：[硕士毕业论文]，大连；大连理工大学，2008
[19] Roberts L G,Machine Perception of three-dimensional solids,Cambridge:MIT Press,1965,159~197
[20] Marr, Vision, W.H. Freeman and Company,1982,46~48
[21] D Beymer, K Konolige. Real-time tracking of multiple people usingcontinuous detection,Proceedings of Intermational Conference on computer Vision,1999
[22] Minoru Asada,Takamaro Tanaka, Visual Tracking Of Unkown MovingObject By Adaptive Binocular Visual Servonig, Proceedings of IntermationalConference on Multisensor Fusion and Intelligent Systems, 1999
[23]张春秀，基于双目视觉的三维重建：[硕士毕业论文]，天津；天津大学，2010
[24]章毓晋，图像工程，北京：清华大学出版社，2007，105~107
[25] S.T. Barnard, M.A. Fischler. Computational Stereo. ACM ComputingSurveys, 1982(4): 553-572
[26] U.R.Dhond and J.K.Aggarwal, Structure from stereo-A Review,IEEETransactions on Systems. Man. and Cybernetics,1989, 19 (6):1489~1510
[27] Koschan, A.What is New in Computational Stereo Since 1989:A Survey ofCurrent Stereo Papers, Technical Report93-22, Univ. of Berlin, 1993
[28] Myron Z.Brown, D.Burschka and G D Halter. Advances in ComputationalStereo.TPAMI, 2005,25 (8)
[29] Scharstein D and Szeliski R. A taxonomy and evaluation of dense two-framestereo correspondence algorithms. International Journal of Computer Vision, 2002,47:7-42
[30] C. Harris, M. Stephens, A combined corner and edge detector, Proceedingsof the Alvey vision Conference, 1988, 189~192
[31] S.M.Smith, J.M.Brady, SUSAN-a new approach to low level imageprocessing. International Journal of Computer Vision, 1997, 23(11): 45~78
[32] Trajkovic,M and Hedley M,“Fast corner detection”,Image and Visioncomputing, Vol18, 1998,75:87
[33]尹世明，立体匹配中的若干问题研究，[硕士毕业论文]，长沙；国防科学技术大学，2006
[34] Z. G Zeng, H.Yan. Region matching and optimal matching pairtheorem,Computer Graphics International, 2001
[35]徐奕，周军，周源华，立体视觉匹配技术，计算机工程与应用，2003，39（15）：1~5
[36] T. Kanade and M.Okutomi, A Stereo Matching Algorithm with An adaptiveWindow: Theory and Experiment, IEEE Transactions on Pattern Analysis andMachine Intelligence, 1994, 16(9), 920~932
[37] Hirschmuller, H.,P.Innocent and J.Garibaldi, Real-Time Correlation-BasedStereo Vision with Reduced Border Errors. International Journal of Computer Vision,2002, 47, 550~580
[38] D. Rosenholm, Multi-point matching using the least-squares technique for anevaluation of three-dimensional models.Photogrammatic Engineering and RemoteSensing,1987,53(6): 1214~1218
[39] Veksler,O. Fast Variable Window for Stereo Correspondence Using IntegralImages, IEEE Conference on Computer Vision and Pattern Recognition, 2003, 1,556~561
[40] Yoon,K.-J. and I.-S.Kweon, Adaptive Support-Weight Approach forCorrespondence Search, IEEE Transactions on Pattern Analysis and MachineIntelligence, 2006, 28(4), 650~656
[41]周秀芝，文贡坚，王润生，自适应窗口快速立体匹配，计算机学报，2006，29（3）：473~479
[42] Zitnick,C.L.and T.Kanade, A Cooperative Algorithm for Stereo Matchingand Occlusion Detection, IEEE Transactions on Pattern Analysis and MachineIntelligence, 2000, 22(7), 675~684
[43] Zitnick C. L., Kanade T., A Cooperative Algorithm for Stereo Matching andOcclusion Detection, CMU Technical Report CMU-RI-TR-99-35, 1999
[44] S. A. Lloyd, E. R. Haddow and J. F. Boyce, A Parallel Binocular StereoAlgorithm Utilizing Dynamic Programming and Relaxation Labeling, ComputerVision, Graphics and Image Processing, 1987, 39, 202~225
[45] Kim C. A dense stereo matching generalized ground control points. usingtwo-pass dynamic programming with In CVPR, 2005, vo1.2: 1075~1082
[46] Roy S.,Cox I. J., A Maximum-Flow 'Formulation of the N-camera StereoCorrespondence Problem, IEEE Proceedings of International Conference onComputer lesion, Bombai, January, 1998:492~499
[47] Bleyer M,Gelautz M. A layered stereo algorithm using image segmentationand global visibility constraints, ISPRS Journal of Photogrammetry and RemoteSensing, 2005, 59 (3) :128~150
[48] Bleyer M,Gelautz M. Graph-cut-based stereo matching using imagesegmentation with symmetrical treat ment of occlusions.Signal Processing:ImageCommunication, 2007, 22 (2) :127~143
[49] V. Kolmogorov and R.Zabih, Computing Visual Correspondence WithOcclusions Using Graph Cuts, International Conference on Computer Vision, 2001,2:508~515
[50] Hong L. and G.Chen, Segment-based Stereo Matching Using Graph Cuts,IEEE Conference on Computer Vision and Pattern Recognition,2004, 1, 74~81
[51] Lhuillier M.,Quan L. Quasi-dense reconstruction from image sequence.In:7th European Conference on Computer Vision,COPENHAGEN ,2002,125~139
[52] Maxime Lhuillier, Long Quan, Robust Dense Matching using Local andGlobal Geometric Constraints. Proceedings of the 15th International Conference onPattern Recognition, Barcelona,Spain, 2000, vol.l:968~972
[53] Z. Megyesi, G. Kos, D. Chetverikov, Dense 3D reconstruction from imagesby normal aided matching. Machine Graphics&Vision International Journal, 15(1):3~28, 2006
[54] M.Habbecke, L. Kobbelt, A Surface-Growing Approach to Multi-ViewStereo Reconstruction.2007
[55]唐丽，基于区域增长的立体像对稠密匹配算法，计算机报，2004，(27)：936~943
[56]刘战杰等，一种新的基于区域生长的彩色图像分割算法，山东大学学报（理学报），2010，145（7）：76~80
[57]唐丽，由手提相机获得的序列图像进行三维重建：[博士毕业论文]，西安；西安电子科技大学，2003
[58] B. B. Alagoz, Obtaining Depth Maps From Color Images By Region BasedStereo Matching Algorithms, OncuBilim Algorithm And Systems Labs. Vol.08,Art.No:04,2008
[59]孟晶晶，基于区域增长的立体匹配算法研究：[硕士毕业论文]，大连；大连理工大学2006
[60] Moravec H.P, Towards automatic visual obstacle avoidance, In 5thInternational Joint Conference on Artificial Intelligence, 1977: 584
[61] Z. Zhang, R.Deriche, O.Faugeras and Q.T.Luong, A robust technique formatching two uncalibrated images through the recovery of Unknown epipolarGeometry, Artificial Intelligence, 1995, 78(1-2): 87~119
[62]徐明亮，卢红星，王琬，OpenGL游戏编程，北京：机械工业社，2008：126~132
[63]安平，立体图像分层交叠块视差估计与自适应补偿，通信学报，2003，24 (3)：1~7
[64] Fua. A parallel stereo algorithm that produces dense depth maps andpreserves image features ,1993
[65] Knight's Quest 3D[EB/OL], http:// www.nvidia.cn/ object/3d-vision-3dmovies-cn.html
[66] Sizzle 3D Stereoscopic Video with Proper 3D Subtitles Overlayed[EB/OL],http://3dvision-blog.com/sizzle-3d-stereoscopic-video-with-proper-3d-subtitles-overlayed/