Depth Extraction Based on Motion Cue and Defocusing Cue
With the development and popularity of stereo images or videos, the requirement of stereo resource is gradually upgrading. As an economical method to solve the problem of stereo resource scarcity, 2D-to-3D video conversion techniques are paid more and more attentions. How to obtain high quality depth information is the key of 2D-to-3D video conversion. Depth information is usually hidden in several interframe cues or pictorial cues. In this paper, motion cue and defocusing cue are analyzed in detail. In order to compensate the limitations of the two cues, the fusion strategy is presented here. The experimental results show that piecewise linear combination of the two cues can improve the quality of depth map.
KeywordsDepth extraction Motion cue Defocusing cue Piecewise linear combination
This work was supported by technological innovation fund of Harbin (2014RFQXJ166) and young creative talent fund of Harbin University of Commerce (2016QN051).
- 1.Vetro, A., Wiegand, T., Sullivan, G.J.: Overview of the stereo and multiview video coding extensions of the H.264/MPEG-4 AVC standard. Proc. IEEE 99(4), 626–642 (2011)Google Scholar
- 2.Feng, X., Guihua, E., Xudong, X.: 2D-to-3D Conversion Based on Motion and Color Mergence. 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video 2008, Istanbul: 3DTV-CON 2008, pp. 205–208 (2008)Google Scholar
- 3.Valenecia, S.A., Rodriguez-Dagnino, R.M.: Synthesizing stereo 3D views from focuscues in monoscopic 2D images. In: Proceedings of SPIE-IS&T Electronic Imaging 5006, pp. 377–388 (2003)Google Scholar
- 4.Malik, A.S., Shim, S.O., Choi, T.S.: Depth map estimation using a robust focus measure. In: 2007 IEEE International Conference on Image Processing, San Antoni: ICIP 2007, pp. 564–567 (2007)Google Scholar
- 5.Jinshun, X., Zhuxing, Y.: Hierarehieal SDD Metrie and Multi-resolution Motion Estimation. Internet Technology Lab. National Sun Yat-Sen University, pp. 46–52 (1994)Google Scholar
- 6.Wien, M.: Variable block-size transforms for H.264/AVC. IEEE Trans. Circ. Syst. Video Technol. 13(7), 604–613 (2003)Google Scholar