Abstract
An efficient method that estimates the depth map of a 3D scene using the motion information of its H.264-encoded 2D video is presented. Our proposed method employs a revised version of the motion information. This is obtained based on the characteristics of the 3D human visual perception. The low complexity of our approach and its compatibility with future broadcasting networks allow its real-time implementation at the receiver, i.e. the 3D signal is delivered at no additional burden to the network. Performance evaluations show that our approach outperforms the other existing H.264-based technique by up to 1.5 dB PSNR i.e. it provides more realistic depth information of the scene. Moreover the subjective comparison of results (obtained by viewers watching the generated stereo video sequences on 3D display system) confirms the higher efficiency of our method.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Zhang, L.: Stereoscopic image generation based on depth images for 3D TV. IEEE Trans. Broadcasting 51(2), 191–199 (2005)
Harman, P., Flack, J., Fox, S., Dowley, M.: Rapid 2D to 3D Conversion. In: Proceedings of SPIE, vol. 4660, pp. 78–86 (2002)
Lai, S.H., Fu, C.W., Chang, S.: A generalized depth estimation algorithm with a single image. PAMI 14(4), 405–411 (1992)
Tam, W.J., Soung Yee, A., Ferreira, J., Tariq, S., Speranza, F.: Stereoscopic image rendering based on depth maps created from blur and edge information. In: Proceedings of Stereoscopic Displays and Applications XII, vol. 5664, pp. 104–115 (2005)
Tam, W.J., Speranza, F., Zhang, L., Renaud, R., Chan, J., Vazquez, C.: Depth image based rendering for multiview stereoscopic displays: Role of information at object boundaries. In: Three-Dimensional TV, Video, and Display IV, vol. 6016, pp. 75–85 (2005)
Ideses, I., Yaroslavsky, L.P., Fishbain, B.: Real-time 2D to 3D video conversion. Journal of Real-Time Image Processing 2(1), 3–9 (2007)
Kim, D., Min, D., Sohn, K.: Stereoscopic video generation method using motion analysis. In: Proceedings of 3DTV Conf., pp. 1–4 (2007)
Scharstein, D.: View Synthesis Using Stereo Vision. LNCS. Springer, Heidelberg (1999)
Richardson, I.E.G.: H.264 and MPEG-4 Video Compression: Video Coding for Next generation Multimedia. John Wiley & Sons, Inc., England (2003)
Vetro, A., Pandit, P., Kimata, H., Smolic, A.: Joint Multiview Video Model (JMVM) 5.0, ISO/IEC JTC1/SC29/WG11/N9214, Lausanne, Switzerland (July 2007)
Fehn, C.: A 3D-TV system based on video plus depth information. Signals, Systems and Computers 2, 1529–1533 (2003)
Methodology for the subjective assessment of the quality of television pictures, ITU-R Recommendation BT.500-11
Scharstain, D.: A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. International Journal of Computer Vision 47, 7–42 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pourazad, M.T., Nasiopoulos, P., Ward, R.K. (2009). Converting H.264-Derived Motion Information into Depth Map. In: Huet, B., Smeaton, A., Mayer-Patel, K., Avrithis, Y. (eds) Advances in Multimedia Modeling . MMM 2009. Lecture Notes in Computer Science, vol 5371. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-92892-8_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-92892-8_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-92891-1
Online ISBN: 978-3-540-92892-8
eBook Packages: Computer ScienceComputer Science (R0)