Share Email Print
cover

Proceedings Paper

2D to 3D conversion implemented in different hardware
Author(s): Eduardo Ramos-Diaz; Victor Gonzalez-Huitron; Volodymyr I. Ponomaryov; Araceli Hernandez-Fragoso
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Conversion of available 2D data for release in 3D content is a hot topic for providers and for success of the 3D applications, in general. It naturally completely relies on virtual view synthesis of a second view given by original 2D video. Disparity map (DM) estimation is a central task in 3D generation but still follows a very difficult problem for rendering novel images precisely. There exist different approaches in DM reconstruction, among them manually and semiautomatic methods that can produce high quality DMs but they demonstrate hard time consuming and are computationally expensive. In this paper, several hardware implementations of designed frameworks for an automatic 3D color video generation based on 2D real video sequence are proposed. The novel framework includes simultaneous processing of stereo pairs using the following blocks: CIE L*a*b* color space conversions, stereo matching via pyramidal scheme, color segmentation by k-means on an a*b* color plane, and adaptive post-filtering, DM estimation using stereo matching between left and right images (or neighboring frames in a video), adaptive post-filtering, and finally, the anaglyph 3D scene generation. Novel technique has been implemented on DSP TMS320DM648, Matlab’s Simulink module over a PC with Windows 7, and using graphic card (NVIDIA Quadro K2000) demonstrating that the proposed approach can be applied in real-time processing mode. The time values needed, mean Similarity Structural Index Measure (SSIM) and Bad Matching Pixels (B) values for different hardware implementations (GPU, Single CPU, and DSP) are exposed in this paper.

Paper Details

Date Published: 27 February 2015
PDF: 12 pages
Proc. SPIE 9400, Real-Time Image and Video Processing 2015, 940006 (27 February 2015); doi: 10.1117/12.2075314
Show Author Affiliations
Eduardo Ramos-Diaz, Univ. Autónoma de la Ciudad de Mexico (Mexico)
Victor Gonzalez-Huitron, Instituto Politécnico Nacional (Mexico)
Volodymyr I. Ponomaryov, Instituto Politécnico Nacional (Mexico)
Araceli Hernandez-Fragoso, Colegio de Estudios de Posgrado de la Ciudad de México (Mexico)


Published in SPIE Proceedings Vol. 9400:
Real-Time Image and Video Processing 2015
Nasser Kehtarnavaz; Matthias F. Carlsohn, Editor(s)

© SPIE. Terms of Use
Back to Top