Browse > Article
http://dx.doi.org/10.5909/JBE.2008.13.4.427

2D-to-3D Stereoscopic conversion: Depth estimation in monoscopic soccer videos  

Ko, Jae-Seung (Visual Information Processing Lab., Information and Communications University)
Kim, Young-Woo (Visual Information Processing Lab., Information and Communications University)
Jung, Young-Ju (Samsung Advanced Institute of Technology)
Kim, Chang-Ick (Visual Information Processing Lab., Information and Communications University)
Publication Information
Journal of Broadcast Engineering / v.13, no.4, 2008 , pp. 427-439 More about this Journal
Abstract
This paper proposes a novel method to convert monoscopic soccer videos to stereoscopic videos. Through the soccer video analysis process, we detect shot boundaries and classify soccer frames into long shot or non-long shot. In the long shot case, the depth mapis generated relying on the size of the extracted ground region. For the non-long shot case, the shot is further partitioned into three types by considering the number of ground blocks and skin blocks which is obtained by a simple skin-color detection method. Then three different depth assignment methods are applied to each non-long shot types: 1) Depth estimation by object region extraction, 2) Foreground estimation by using the skin block and depth value computation by Gaussian function, and 3)the depth map generation for shots not containing the skin blocks. This depth assignment is followed by stereoscopic image generation. Subjective evaluation comparing generated depth maps and corresponding stereoscopic images indicate that the proposed algorithm can yield the sense of depth from a single view images.
Keywords
2D-to-3D conversion; soccer video analysis; 3DTV; depth map;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Jaeseung Ko, Manbae Kim, and Changick Kim, "2D-to-3D stereoscopic conversion: depth-map estimation in a 2D single-view image," in Proc. Of SPIE, Vol. 6696, (2007)
2 lkwon Park, Manbae Kim, and Hyeran Byun, "Robust Zooming Motion Detection for Motion-based stereoscopic conversion," International Workshop on Advanced Image echnology 2007 (IWAIT 2007), pp.370-374, 2007
3 Keewon Seo, Jaeseung Ko, Ilkoo Ahn and Changick Kim, "An Intelligent Display Scheme of Soccer Video for Mobile Devices," IEEE Transactions on Circuits and Systems for Video Technology (CSVT), vol.17, no.10, pp.1395-1401, October 2007   DOI   ScienceOn
4 R. C. Gonzalez, R.E. Woods, Digital Image Processing Second Edtion, Prentice Hall, 2002, pp. 295- 302
5 J. Kim, Y. Kim, J. Park, Jin-mo Kang, and B. Lee, "Stereoscopic conversion of two-dimensional movie encoded in MPEG-2," in Proc. Of SPIE, Vol. 6311 (2006)
6 W.J Tam, F. Speranza, L.Zhang, R. Renaud, J. Chan, and C. Vazquez, "Depth image based rendering for multiview stereoscopic displays: Role of information at object boundaries," in Proc. of the SPIE, Vol. 6016, pp. 75-85 (2005)
7 Battiato, S.; Capra, A.; Curti, S.; and La Cascia, M, "3D Stereoscopic Image Pairs by Depth-Map Generation", in Proc. of 2nd International Symposium on 3D Data Processing Visualiza- tion and Transmission, 3DPVT(2004)
8 S.A. Valencia, R.M. Rodriguez-Dagnino, "Synthesizing Stereo 3D View from Focus Cues in Monoscopic 2D Images¡," in Proc. Of SPIE, Vol. 5006, pp.377-388 (2003)   DOI
9 B.J. Garcia "Approaches to stereoscopic video based on spatiotemporal interpolation," in Proc. Of SPIE, Vol. 2653, pp. 85-95 (1996)   DOI
10 T. Okino, H. Murata, K, Taima, T. Iinuma, and K. Oketani, "New television with 2D/3D image conversion technologies," in Proc. Of SPIE, Vol. 2653, pp. 96-103 (1996)   DOI