Abstract
In 2D-to-3D video conversion, key-frame selection is essential and it affects the quality and workload of the conversion. In this paper, a key-frame selection method based on edge classification is proposed. In the proposed method, the candidate key-frames are selected out based on the occlusion area and feature point correspondence. The optimal key-frames are selected out from the candidates according to the edge point classification so that the depth of the key-frames can be estimated accurately and automatically referring to the depth estimation based on focus cue. Experiments show that the proposed method can bring 2D-to-3D conversion better objective and subject quality and it is promising in practical applications.
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.
Similar content being viewed by others
References
Varekamp, C., Barebrug, B.: Improved Depth Propagation for 2D-to-3D Video Conversion Using Key-Frames. In: The 4th European Conference on Visual Media Production, pp. 1–7 (2007)
Li, Y., Sun, J., Tang, C.K., Shum, H.Y.: Lazy Snapping. ACM Transaction on Graphics 23, 303–308 (2004)
Bai, X., Wang, J., Simons, D., Sapiro, G.: Video Snapcut: Robust Video Object Cutout Using Localized Classifiers. ACM Transaction on Graphics 28, 617–630 (2009)
Rotem, E., Wolowelsky, K., Pelz, D.: Automatic Video to Stereoscopic Video Conversion. In: Proceedings of the SPIE, vol. 5664, pp. 198–204 (2005)
Cao, X., Li, Z., Dai, Q.H.: Semi-automatic 2D-to-3D Conversion Using Disparity Propagation. IEEE Transaction on Broadcasting 57(2), 491–499 (2011)
Gunsel, B., Tekalp, A.M., Peter, J.L.: Moving Visual Representation of Video Objects for Content-based Search and Browsing. In: Proceedings of the ICIP, pp. 502–505 (1997)
Zhang, H.J., Wang, Y.A., Altunbasak, Y.: Content Based Video Retrieval and Compression: A Unified Solution. In: Proceedings of the ICIP, pp. 13–16 (1997)
Qi, G., Ko, C.C., Sliva, L.C.: A Universal Scheme for Content-based Video Representation and Indexing. In: Proceedings of the IEEE APCCAS, pp. 469–472 (2000)
Jia, C., Hou, W.Q., Xu, Y.K.: A New Approach of Key Frame Extraction. Microcomputer Information 21, 133–134 (2007)
Nistér, D.: Frame Decimation for Structure and Motion. In: Second European Workshop on 3D Structure from Multiple Images of Large-Scale Environment, pp. 17–34 (2000)
Gibson, S., Cook, J., Howard, T., Hubbold, R.: Accurate Camera Calibration for Off-line, Video-based Augmented Reality. In: The 1st International Symposium on Mixed and Augmented Reality, pp. 37–46 (2002)
Sun, J.D., Xie, J.C., Liu, J., Shen, Y.J.: Dual Threshold Based Key-frame Selection for 2D-to-3D Conversion. Journal of Computational Information Systems 9(4), 1297–1305 (2013)
Valencia, S.A., Rodríguez-Dagnino, R.M.: Synthesizing Stereo 3D Views from Focus Cues in Monoscopic 2D images. In: Proceedings of the SPIE, vol. 5006, pp. 377–388 (2003)
Guo, G., Zhang, N., Huo, L.S., Gao, W.: 2D to 3D Conversion Based on Edge Defocus and Segmentation. In: Proceedings of the ICASSP, pp. 2181–2184 (2008)
Boykov, Y., Veksler, O., Zabih, R.: Efficient Approximate Energy Minimization via Graph Cuts. IEEE Transactions on PAMI 20(12), 1222–1239 (2001)
Kolmogorov, V., Zabih, R.: What Energy Functions can be Minimized via Graph Cuts? IEEE Transactions on PAMI 26(2), 147–159 (2004)
Boykov, Y., Kolmogorov, V.: An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. IEEE Transactions on PAMI 26(9), 1124–1137 (2004)
Mallat, S., Zhong, S.: Characterization of Signals from Multiscale Edges. IEEE Transactions on PAMI 14, 710–732 (1992)
Mallat, S.G., Hwang, W.L.: Singularity Detection and Processing with Wavelet. IEEE Transaction on Information Theory 38(2), 617–643 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xie, J., Sun, J., Liu, J., Hu, Q. (2013). Key-Frame Selection Strategy Based on Edge Points Classification in 2D-to-3D Conversion. In: Sun, C., Fang, F., Zhou, ZH., Yang, W., Liu, ZY. (eds) Intelligence Science and Big Data Engineering. IScIDE 2013. Lecture Notes in Computer Science, vol 8261. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42057-3_100
Download citation
DOI: https://doi.org/10.1007/978-3-642-42057-3_100
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42056-6
Online ISBN: 978-3-642-42057-3
eBook Packages: Computer ScienceComputer Science (R0)