Automatic stereoscopic 3D video reframing

Author

Coria, Lino ; Xu, Di ; Nasiopoulos, Panos

Author_Institution

Univ. of British Columbia, Vancouver, BC, Canada

fYear

2012

fDate

15-17 Oct. 2012

Firstpage

1

Lastpage

4

Abstract

3D displays have various aspect ratios (e.g., 16:9, 4:3, and 3:2). Watching 3D videos with the wrong aspect ratio decreases the quality of the viewing experience. We have developed a smart reframing solution that uses a visual attention model for stereoscopic 3D video to identify the prominent visual regions of every stereoscopic frame. Our method uses several saliency indicators such as depth, edges, brightness, color, and movement. Additionally, our method provides a dynamic cropping window that slides smoothly from frame to frame.

Keywords

stereo image processing; three-dimensional displays; video signal processing; 3D display; automatic stereoscopic 3D video reframing; dynamic cropping window; saliency indicator; video quality; visual attention model; Cameras; Color; Computational modeling; Solid modeling; Stereo image processing; Three dimensional displays; Visualization; 3D; 3D TV; 3D displays; aspect ratio; depth map; quaternion; reframing; saliency map; stereoscopic; texture map; visual attention model;

fLanguage

English

Publisher

ieee

Conference_Titel

3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), 2012

Conference_Location

Zurich

ISSN

2161-2021

Print_ISBN

978-1-4673-4904-8

Electronic_ISBN

2161-2021

Type

conf

DOI

10.1109/3DTV.2012.6365428

Filename

6365428