Abstract
Rather than based on the stereo vision principle and the relationship between the camera position and the video scene objects used in most of current 2D-to-3D video conversion algorithms, a new prediction method of video depth information based on video frame differences is proposed and implemented on an embedded platform in this paper. 3D stereoscopic video sequences are generated by using the original 2D video sequences and the depth information. The theoretical analysis and experimental results have showed that the proposed method is more feasible and efficiency compared with the current algorithms.
Publisher
Trans Tech Publications, Ltd.
Reference12 articles.
1. Ollis,M., Williamson, The future of 3D video, Computer[J], 2001, 34(6): 92-99.
2. C. Fehn, R. S. Pastoor. Interactive 3-DTV concepts and key technologies [J]. Proceedings of the IEEE, 2006, 94(3): 524-538.
3. P. Harman, J. Flack, S. Fox, M. Dowley, Rapid 2D to 3D Conversion, In Proc. SPIE Vol. 4660, Stereoscopic Displays and Virtual Reality Systems IX, pp.78-86, (2002).
4. J.R. Smith, Shih-Fu Chang, Multi-stage Classification of Image from Futures and Related Text, In Proc. of Fourth DELOS workshop, Pisa, Italy, August, (1997).
5. C. Fehn. Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV[C]. Proc. of the SPIE, 2004: 93-104.