Abstract
A procedure is described for stereoscopic videoconference system with viewpoint adaptation. The core to such a system is to synthesize the intermediate views from stereoscopic videoconference images with rather large baseline. The foreground object is first segmented by using intensity and disparity information. For this purpose, the region growing technique is used. The reliability of disparity estimation is then measured with a criterion based on uniqueness and smoothness constrains. In occluded areas and image points with unreliable disparity assignments, region-based interpolation strategy is applied to compensate the disparity values. Finally, an object-based interpolation algorithm is developed to synthesize arbitrary intermediate views. Experimental results with natural stereoscopic image pairs show that the proposed method can obtain the intermediate views with high quality.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Jens-Rainer, O., Izquierdo, E.: An Object-based System for Stereoscopic Viewpoint Synthesis. IEEE Transactions on Circuits and Systems for Video Technology 7, 801–811 (1997)
McVeigh, J., Siegel, M., Jordan, A.: Intermediate View Synthesis Considering Occluded and Ambiguously Referenced Image Regions. Signal Processing: Image Communication 9, 21–28 (1996)
Izquierdo, E.: Stereo Matching for Enhanced Telepresence in Three-Dimensional Videocommunications. IEEE Transactions on Circuits and Systems for Video Technology 7, 629–643 (1997)
Izquierdo, E.: Stereo Image Analysis for Muti-viewpoint Telepresence Applications. Signal Processing: Image Communication 11, 231–254 (1998)
Zhang, L., Wang, D., Vincent, A.: Reliability Measurement of Disparity Estimates for Intermediate View Reconstruction. In: Proceedings of IEEE Int. Conf. on Image Processing, vol. 3, pp. 24–28 (2002)
Werner, T., Hersch, R.D., Hlavac, V.: Rendering Real World Objects Using View Interpolation. In: Proceedings of IEEE Int. Conf. Computer Vision, Boston, MA, pp. 957–962 (1995)
Mansouri, A.R., Konrad, J.: Bayesian Winner-take-all Reconstruction of Intermediate Views from Stereoscopic Images. IEEE Trans. on Image Processing 9, 1–13 (2000)
Nikolaos, D.D., Anastasios, D.D., Yannis, S.A., Klimis, S.N., Stefanos, D.K.: Efficient Summarization of Stereoscopic Video Sequences. IEEE Trans. Circuits Sys. Video Technol. 10, 501–517 (2000)
Xia, L.Z.: Digital Image Processing. Nanjing (1999)
Wang, D., Lauzon, D.: Hybrid Algorithm for Estimating True Motion Field. Optical Engineering 39, 2876–2881 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lu, C., An, P., Zhang, Z. (2004). Intermediate View Synthesis from Stereoscopic Videoconference Images. In: Laganá, A., Gavrilova, M.L., Kumar, V., Mun, Y., Tan, C.J.K., Gervasi, O. (eds) Computational Science and Its Applications – ICCSA 2004. ICCSA 2004. Lecture Notes in Computer Science, vol 3046. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24768-5_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-24768-5_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22060-2
Online ISBN: 978-3-540-24768-5
eBook Packages: Springer Book Archive