Fast 3D computational integral imaging using graphics processing unit

Faliu Yi; Inkyu Moon; Jeong A. Lee; Bahram Javidi

doi:10.1109/JDT.2012.2219498

Fast 3D computational integral imaging using graphics processing unit

Faliu Yi, Inkyu Moon, Jeong A. Lee, Bahram Javidi

Department of Robotics and Mechatronics Engineering

Research output: Contribution to journal › Article › peer-review

29 Scopus citations

Abstract

In computational integral imaging (II), the elemental images are processed on serial processors to reconstruct one plane (slice) of the 3D scene. In this paper, we present a fast three-dimensional (3D) integral imaging system via a graphics processing unit (GPU) which allows parallel processing with multiple processors. We show that it can significantly accelerate 3D scene reconstruction in II using the GPU based stream-processing model. The streaming version of the ray back propagation algorithm with lookup table is presented. It is demonstrated that the ray back propagation algorithm with a lookup table for the 3D scene reconstruction in II to be processed on parallel processors may greatly improve computational speed while requiring minimally larger memory space as compared with CPU sequential computing. Experimental results verify the feasibility for parallel implementation of 3D integral imaging. To the best of our knowledge, this is the first study on achieving a 3D computational integral imaging system using GPU computing with high parallelism.

Original language	English
Article number	6341092
Pages (from-to)	714-722
Number of pages	9
Journal	IEEE/OSA Journal of Display Technology
Volume	8
Issue number	12
DOIs	https://doi.org/10.1109/JDT.2012.2219498
State	Published - 2012

Bibliographical note

Funding Information:
Manuscript received July 19, 2012; accepted September 07, 2012. Date of publication October 26, 2012; date of current version November 20, 2012. This work was supported by Mid-career Researcher Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology under 2010-0010391. (Corresponding author: I. Moon.) F. Yi, I. Moon, and J.-A. Lee are with the School of Computer Engineering, Chosun University, Dong-gu, Gwangju, 501-759 Korea (e-mail: [email protected]; inkyu.moon@ chosun.ac.kr; [email protected]).

Keywords

Graphics processing unit (GPU)
integral imaging (II)
parallel processing
three-dimensional (3D) image processing

Access to Document

10.1109/JDT.2012.2219498

Cite this

@article{c6eeaebbac1445a5b710b0b52ad4db78,

title = "Fast 3D computational integral imaging using graphics processing unit",

abstract = "In computational integral imaging (II), the elemental images are processed on serial processors to reconstruct one plane (slice) of the 3D scene. In this paper, we present a fast three-dimensional (3D) integral imaging system via a graphics processing unit (GPU) which allows parallel processing with multiple processors. We show that it can significantly accelerate 3D scene reconstruction in II using the GPU based stream-processing model. The streaming version of the ray back propagation algorithm with lookup table is presented. It is demonstrated that the ray back propagation algorithm with a lookup table for the 3D scene reconstruction in II to be processed on parallel processors may greatly improve computational speed while requiring minimally larger memory space as compared with CPU sequential computing. Experimental results verify the feasibility for parallel implementation of 3D integral imaging. To the best of our knowledge, this is the first study on achieving a 3D computational integral imaging system using GPU computing with high parallelism.",

keywords = "Graphics processing unit (GPU), integral imaging (II), parallel processing, three-dimensional (3D) image processing",

author = "Faliu Yi and Inkyu Moon and Lee, {Jeong A.} and Bahram Javidi",

note = "Funding Information: Manuscript received July 19, 2012; accepted September 07, 2012. Date of publication October 26, 2012; date of current version November 20, 2012. This work was supported by Mid-career Researcher Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology under 2010-0010391. (Corresponding author: I. Moon.) F. Yi, I. Moon, and J.-A. Lee are with the School of Computer Engineering, Chosun University, Dong-gu, Gwangju, 501-759 Korea (e-mail: [email protected]; inkyu.moon@ chosun.ac.kr; [email protected]).",

year = "2012",

doi = "10.1109/JDT.2012.2219498",

language = "English",

volume = "8",

pages = "714--722",

journal = "IEEE/OSA Journal of Display Technology",

issn = "1551-319X",

publisher = "IEEE Computer Society",

number = "12",

}

TY - JOUR

T1 - Fast 3D computational integral imaging using graphics processing unit

AU - Yi, Faliu

AU - Moon, Inkyu

AU - Lee, Jeong A.

AU - Javidi, Bahram

N1 - Funding Information: Manuscript received July 19, 2012; accepted September 07, 2012. Date of publication October 26, 2012; date of current version November 20, 2012. This work was supported by Mid-career Researcher Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology under 2010-0010391. (Corresponding author: I. Moon.) F. Yi, I. Moon, and J.-A. Lee are with the School of Computer Engineering, Chosun University, Dong-gu, Gwangju, 501-759 Korea (e-mail: [email protected]; inkyu.moon@ chosun.ac.kr; [email protected]).

PY - 2012

Y1 - 2012

N2 - In computational integral imaging (II), the elemental images are processed on serial processors to reconstruct one plane (slice) of the 3D scene. In this paper, we present a fast three-dimensional (3D) integral imaging system via a graphics processing unit (GPU) which allows parallel processing with multiple processors. We show that it can significantly accelerate 3D scene reconstruction in II using the GPU based stream-processing model. The streaming version of the ray back propagation algorithm with lookup table is presented. It is demonstrated that the ray back propagation algorithm with a lookup table for the 3D scene reconstruction in II to be processed on parallel processors may greatly improve computational speed while requiring minimally larger memory space as compared with CPU sequential computing. Experimental results verify the feasibility for parallel implementation of 3D integral imaging. To the best of our knowledge, this is the first study on achieving a 3D computational integral imaging system using GPU computing with high parallelism.

AB - In computational integral imaging (II), the elemental images are processed on serial processors to reconstruct one plane (slice) of the 3D scene. In this paper, we present a fast three-dimensional (3D) integral imaging system via a graphics processing unit (GPU) which allows parallel processing with multiple processors. We show that it can significantly accelerate 3D scene reconstruction in II using the GPU based stream-processing model. The streaming version of the ray back propagation algorithm with lookup table is presented. It is demonstrated that the ray back propagation algorithm with a lookup table for the 3D scene reconstruction in II to be processed on parallel processors may greatly improve computational speed while requiring minimally larger memory space as compared with CPU sequential computing. Experimental results verify the feasibility for parallel implementation of 3D integral imaging. To the best of our knowledge, this is the first study on achieving a 3D computational integral imaging system using GPU computing with high parallelism.

KW - Graphics processing unit (GPU)

KW - integral imaging (II)

KW - parallel processing

KW - three-dimensional (3D) image processing

UR - http://www.scopus.com/inward/record.url?scp=84870564587&partnerID=8YFLogxK

U2 - 10.1109/JDT.2012.2219498

DO - 10.1109/JDT.2012.2219498

M3 - Article

AN - SCOPUS:84870564587

SN - 1551-319X

VL - 8

SP - 714

EP - 722

JO - IEEE/OSA Journal of Display Technology

JF - IEEE/OSA Journal of Display Technology

IS - 12

M1 - 6341092

ER -

Fast 3D computational integral imaging using graphics processing unit

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this