@inproceedings{444274a877d04422999c70f3880320f8,
title = "Automatic 2D-to-3D video conversion by monocular depth cues fusion and utilizing human face landmarks",
abstract = "In this paper, we propose a hybrid 2D-to-3D video conversion system to recover the 3D structure of the scene. Depending on the scene characteristics, geometric or height depth information is adopted to form the initial depth map. This depth map is fused with color-based depth cues to construct the nal depth map of the scene background. The depths of the foreground objects are estimated after their classi cation into human and non-human regions. Speci cally, the depth of a non-human foreground object is directly calculated from the depth of the region behind it in the background. To acquire more accurate depth for the regions containing a human, the estimation of the distance between face landmarks is also taken into account. Finally, the computed depth information of the foreground regions is superimposed on the background depth map to generate the complete depth map of the scene which is the main goal in the process of converting 2D video to 3D.",
keywords = "2D-to-3D video conversion, Anthropometric-based cue, Color-based depth cue, Geometric depth cues, Height depth cue",
author = "Fard, {Mani B.} and Ulug Bayazit",
year = "2013",
doi = "10.1117/12.2049802",
language = "English",
isbn = "9780819499967",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
booktitle = "Sixth International Conference on Machine Vision, ICMV 2013",
address = "United States",
note = "6th International Conference on Machine Vision, ICMV 2013 ; Conference date: 16-11-2013 Through 17-11-2013",
}