DOI QR코드

DOI QR Code

2D/3D 동영상 변환을 위한 그룹화된 객체별 깊이 정보의 차등 적용 기법

Applying differential techniques for 2D/3D video conversion to the objects grouped by depth information

  • 투고 : 2012.01.02
  • 심사 : 2012.03.08
  • 발행 : 2012.03.31

초록

본 논문은 2D/3D 동영상 변환을 위한 그룹화된 객체별 깊이 정보의 차등 적용 기법에 관한 연구이다. 기존의 깊이 정보 획득 기법 중 움직임 정보를 깊이 정보로써 사용할 때 움직임이 존재하지 않는 객체의 경우 깊이 정보를 획득할 수 없어 해당 객체의 3D 효과를 얻을 수 없는 문제점이 있다. 본 논문에서는 이러한 문제점을 해결하고자 객체와 배경을 추출하고 객체에 움직임 정보를 이용한 깊이 정보를 할당하는 과정을 거친 후, 배경과 깊이 정보가 할당되지 못한 객체에 깊이 단서 중 하나인 상대적 높이 단서를 이용한 깊이 정보를 할당함으로써 모든 객체에서 3D 효과를 얻을 수 있는 기법을 제안한다. 제안한 기법으로 깊이맵을 생성하여 DIBR(Depth Image Based Rendering)으로 3D 영상을 생성하여 확인한 결과 움직임이 없는 객체에서도 3D 효과를 얻을 수 있음을 확인하였다.

In this paper, we propose applying differential techniques for 2D/3D video conversion to the objects grouped by depth information. One of the problems converting 2D images to 3D images using the technique tracking the motion of pixels is that objects not moving between adjacent frames do not give any depth information. This problem can be solved by applying relative height cue only to the objects which have no moving information between frames, after the process of splitting the background and objects and extracting depth information using motion vectors between objects. Using this technique all the background and object can have their own depth information. This proposed method is used to generate depth map to generate 3D images using DIBR(Depth Image Based Rendering) and verified that the objects which have no movement between frames also had depth information.

키워드

참고문헌

  1. L. Zhang, C. Vázquez, and S. Knorr, "3D-TV Content Creation: Automatic 2D-to-3D Video Conversion," (invited paper) IEEE Trans. on Broadcasting, Special Issue on 3D-TV, 2011.
  2. Hyeon Ho Han, Gang Seong Lee, Sang Hun Lee, "A Study on 2D/3D image Conversion Method using Create Depth Map", Journal of The Korea Academia-Industrial cooperation Society, Vol 12, no. 4 pp. 1897-1903, 2011. https://doi.org/10.5762/KAIS.2011.12.4.1897
  3. T. Okino, H. Murata, "New Television with 2D/3D image conversion technologies", SPIE Vol. 2653, pp. 96-103, 1996
  4. Baxter J. Garcia "Approaches to stereoscopic video based on spatio-temporal interpolation," SPIE Vol. 2653, pp.85-95, 1990
  5. C. Fehn, "Depth-image-based rendering (DIBR), compression and transmission for a new approach on 3D-TV", Proceeding of the SPIE Stereoscopic Displays and Virtual Reality Systems XI, Vol. 5291, pp. 93-104, 2004.
  6. Deqing Sun, Roth, S., Black, M. J., "Secret of Optical Flow Estimation and Their Principles", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2432-2439, 2010.
  7. L. Zhang, B. Lawrence, D. Wang, and A. Vincent, "Comparison study on feature matching and block matching for automatic 2D to 3D video conversion," in The Second IEE European Conference on Visual Media Production (CVMP 2005), London, UK, pp. 122-129, 2005,
  8. Sudong Kim, Jisang Yoo, "3D conversion of 2D video using depth layer partition", Journal of Broadcast Engineering, Vol. 16 No. 1 pp. 44-53, 2011 https://doi.org/10.5909/JEB.2011.16.1.044
  9. Jianbo Shi and Jitendra Malik, "Normalized Cuts and Image Segmentation", IEEE transactions on pattern analysis and machine intelligence, Vol. 22, pp. 888-905, 2000. https://doi.org/10.1109/34.868688
  10. Sung Ho Han, Yeong Pyo Hong, Jong Youn Lee, Sang Hun Lee, "2D/3D Video Conversion Method using Differential Depth Information by Grouped Object", Proceedings of the KAIS Fall conference, Vol 12, no 2 pp. 445-448, 2011.
  11. L. Zhang, W. J. Tam, "Stereoscopic image generation based on depth images for 3D TV", IEEE Trans. on Broadcasting, Vol. 51, no. 2 pp. 191-199, 2005. https://doi.org/10.1109/TBC.2005.846190

피인용 문헌

  1. Automatic salient object segmentation using saliency map and color segmentation vol.20, pp.9, 2013, https://doi.org/10.1007/s11771-013-1750-1