基于分段化结构重建的2D/3D视频转换方法

刘伟; 李功燕; 丁锴; 吴毅红

doi:10.13700/j.bh.1001-5965.2013.0437

基于分段化结构重建的2D/3D视频转换方法

doi: 10.13700/j.bh.1001-5965.2013.0437

1. 中国科学院微电子研究所物联网中心, 北京 100029;
2. 北京航空航天大学自动化科学与电气工程学院, 北京 100191;
3. 中国科学院自动化研究所模式识别国家重点实验室, 北京 100190

详细信息

作者简介:
刘伟（1983- ），男，河南南阳人，助理研究员，lw3171796@163.com.

中图分类号: TP391
计量
- 文章访问数: 1634
- HTML全文浏览量: 198
- PDF下载量: 576
- 被引次数: 0
出版历程
- 收稿日期: 2013-07-30
- 网络出版日期: 2014-06-20

2D/3D video conversion method based on piece-wise structure from motion

1. Center for Internet of Things, Institute of Microelectronics of Chinese Academy of Sciences, Beijing 100029, China;
2. School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China;
3. National Laboratory of Pattern Recognition, Institute of Automation of Chinese Academy of Sciences, Beijing 100190, China

摘要

摘要: 为了缓解3D片源的不足，设计了一种分段化结构重建方法为视频2D/3D转换提供深度线索.采用分层提取的方式，将视频基于内容分解为子序列，在每个子序列中建立优化准则选择出处于非退化状态的关键帧，并以此为基础提出了分段化结构重建框架，利用改进的耦合自标定算法重构出每个子序列对应的离散3D结构信息，从而获取视频的深度线索.实验结果表明，该方法通过分段化后的局部优化，不仅使结构化重建能够有效处理多场景下的连续镜头，还加快了转换的效率，能够稳定、高效地获取深度信息，适用于视频2D/3D转换.
- 2D/3D /
- 关键帧 /
- 结构重建 /
- 深度线索
Abstract: To alleviate the shortage of 3D media sources, a piece-wise structure from motion method was designed to provide depth cues for the 2D/3D video conversion. Videos were decomposed into subsequences of different scenes and key frames of non-degenerate were extracted in each subsequence with optimization criteria. On this basis, a piece-wise structure from motion framework was proposed and depth cues of scene sparse structures were obtained through an improved coupling self-calibration algorithm. Experimental results show that by local optimization after video segmentation, the proposed method can handle video shot containing multiple scenes based on structure from motion, and improve the efficiency of conversion effectively. Those mean the proposed method is suitable for the 2D/3D video conversion.
- 2D/3D /
- key frames /
- structure from motion /
- depth cues

HTML全文

参考文献(17)

[1]	刘伟,吴毅红, 胡占义.电影2D/3D转换技术概述[J].计算机辅助设计与图形学学报,2012,24(1):14-28 Liu Wei.Wu Yihong.Hu Zhanyi.A survey of 2D to 3D conversion technology for film[J].Journal of Computer-Aided Design & Computer Graphics,2012,24(1):14-28(in Chinese)
[2]	Nam S W, Kim H S,Ban Y J,et al.Real-time 2D to 3D conversion for 3DTV using time coherent depth map generation method[C]//Proceedings IEEE Conference on Consumer Electronics.Piscataway,NJ:IEEE,2013:187-188
[3]	Feng Y, Ren J,Jiang J M.Object-based 2D-to-3D video conversion for effective stereoscopic content generation in 3D-TV application[J].IEEE Transactions on Broadcasting,2011,57(2):500-509
[4]	Tsai Y M, Chang Y L,Chen L G.Block-based vanishing line and vanishing point detection for 3d scene reconstruction[C]//Proceedings International Symposium on Intelligent Signal Processing and Communication Systems.Piscataway,NJ:IEEE,2007:586-589
[5]	郑芳炫,杨志强. 以消失点为基础下从单张影像中估测深度[J].信息技术与应用,2006,1(3):229-235 Zheng Fangxuan,Yang Zhiqiang.Depth estimation from single image based on vanishing point[J].Journal of Information Technology and Applications,2006,1(3):229-235(in Chinese)
[6]	Jung Y J, Baik A,Kim J,et al.A novel 2D-to-3D conversion technique based on relative height-depth cue[C]//Proceedings SPIE.Bellingham:SPIE Press,2009,7237:72371U
[7]	Guo G, Zhang N,Huo L S,et al.2D to 3D conversion based on edge defocus and segmentation[C]//Proceedings IEEE International Conference on Acoustics Speech and Signal.Los Alamitos:IEEE Computer Society Press,2008:2181-2184
[8]	Ko J, Kim M,Kim C.2D-To-3D stereoscopic conversion:depth-map estimation in a 2D single-view image[C]//Proceedings SPIE.Bellingham:SPIE Press,2007,6696:66962A
[9]	Cigla C, Alatan A A.Real-time stereo matching algorithm for 3DTV[C]//Proceedings Signal Processing and Communications Applications Conference.Piscataway,NJ:IEEE Computer Society Press,2012:6204481
[10]	Saxena A, Chung S H,Ng A Y.3D depth reconstruction from a single still image[J].International Journal of Computer Vision,2008,76(1):53-69
[11]	Kim J, Baik A,Jung Y J,et al.2D-to-3D conversion by using visual attention analysis[C]//Proceedings SPIE.Bellingham:SPIE Press,2010,7524:752412
[12]	Lang M, Hornung A,Wang O,et al.Nonlinear disparity mapping for stereoscopic 3D[C]//ACM Transactions on Graphics.New York:ACM Press,2010,29(4):75
[13]	Rotem E, Wolowelsky K,Pelz D.Automatic video to stereoscopic video conversion[C]//Proceedings SPIE.Bellingham:SPIE Press,2005,5664:198-206
[14]	Knorr S, Smolic A,Sikora T.From 2D-to stereo-to multi-view video[C]//Proceedings 3DTV-Conference.Piscataway,NJ:IEEE Computer Society Press,2007:4379455
[15]	Repko J, Pollefeys M.3D models from extended uncalibrated video sequences.addressing key-frame selection and projective drift[C]//Proceedings 3D Digital Imaging and Modeling.Washington,DC:IEEE Computer Society,2005:150-157
[16]	Liu T C, Kender J R.Computational approaches to temporal sampling of video sequences[J].ACM Transactions on Multimedia Computing,Communications,and Applications,2007, 3(2): 7-29
[17]	Hartley R, Zisserman A.Multiple view geometry [M].Cambridge:Cambridge University Press,2003:262-276