Real-time object segmentation based on GPU

Sun J. Lee, Chang-Sung Jeong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper we present a new novel GPU-based algorithm for real time object segmentation by employing several techniques which make use of framebuffer, Swizzle operator, stencil buffer and the other factors on GPU. Frame buffer is used for the fast processing of image on GPU without going back and forth to the CPU, swizzle operator for the efficient and fast execution of vector operations for object segmentation, and stencil buffer for the fast computation of the masked area for the detected object, thus speeding up the whole algorithm sharply. Moreover, the computation of the histograms and bounding boxes make our algorithm very simple and fast by using 'gather' operation uniquely supported by GPU. Our experimental results have shown that our algorithm is much faster than CPU based one.

Original languageEnglish
Title of host publication2006 International Conference on Computational Intelligence and Security, ICCIAS 2006
Pages739-742
Number of pages4
Volume1
DOIs
Publication statusPublished - 2007 Dec 1
Event2006 International Conference on Computational Intelligence and Security, ICCIAS 2006 - Guangzhou, China
Duration: 2006 Oct 32006 Oct 6

Other

Other2006 International Conference on Computational Intelligence and Security, ICCIAS 2006
CountryChina
CityGuangzhou
Period06/10/306/10/6

Fingerprint

Program processors
Graphics processing unit
Processing

ASJC Scopus subject areas

  • Computer Science(all)
  • Control and Systems Engineering

Cite this

Lee, S. J., & Jeong, C-S. (2007). Real-time object segmentation based on GPU. In 2006 International Conference on Computational Intelligence and Security, ICCIAS 2006 (Vol. 1, pp. 739-742). [4072185] https://doi.org/10.1109/ICCIAS.2006.294232

Real-time object segmentation based on GPU. / Lee, Sun J.; Jeong, Chang-Sung.

2006 International Conference on Computational Intelligence and Security, ICCIAS 2006. Vol. 1 2007. p. 739-742 4072185.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, SJ & Jeong, C-S 2007, Real-time object segmentation based on GPU. in 2006 International Conference on Computational Intelligence and Security, ICCIAS 2006. vol. 1, 4072185, pp. 739-742, 2006 International Conference on Computational Intelligence and Security, ICCIAS 2006, Guangzhou, China, 06/10/3. https://doi.org/10.1109/ICCIAS.2006.294232
Lee SJ, Jeong C-S. Real-time object segmentation based on GPU. In 2006 International Conference on Computational Intelligence and Security, ICCIAS 2006. Vol. 1. 2007. p. 739-742. 4072185 https://doi.org/10.1109/ICCIAS.2006.294232
Lee, Sun J. ; Jeong, Chang-Sung. / Real-time object segmentation based on GPU. 2006 International Conference on Computational Intelligence and Security, ICCIAS 2006. Vol. 1 2007. pp. 739-742
@inproceedings{077d7fab56fc492a91ea3dab877e752c,
title = "Real-time object segmentation based on GPU",
abstract = "In this paper we present a new novel GPU-based algorithm for real time object segmentation by employing several techniques which make use of framebuffer, Swizzle operator, stencil buffer and the other factors on GPU. Frame buffer is used for the fast processing of image on GPU without going back and forth to the CPU, swizzle operator for the efficient and fast execution of vector operations for object segmentation, and stencil buffer for the fast computation of the masked area for the detected object, thus speeding up the whole algorithm sharply. Moreover, the computation of the histograms and bounding boxes make our algorithm very simple and fast by using 'gather' operation uniquely supported by GPU. Our experimental results have shown that our algorithm is much faster than CPU based one.",
author = "Lee, {Sun J.} and Chang-Sung Jeong",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICCIAS.2006.294232",
language = "English",
isbn = "1424406056",
volume = "1",
pages = "739--742",
booktitle = "2006 International Conference on Computational Intelligence and Security, ICCIAS 2006",

}

TY - GEN

T1 - Real-time object segmentation based on GPU

AU - Lee, Sun J.

AU - Jeong, Chang-Sung

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper we present a new novel GPU-based algorithm for real time object segmentation by employing several techniques which make use of framebuffer, Swizzle operator, stencil buffer and the other factors on GPU. Frame buffer is used for the fast processing of image on GPU without going back and forth to the CPU, swizzle operator for the efficient and fast execution of vector operations for object segmentation, and stencil buffer for the fast computation of the masked area for the detected object, thus speeding up the whole algorithm sharply. Moreover, the computation of the histograms and bounding boxes make our algorithm very simple and fast by using 'gather' operation uniquely supported by GPU. Our experimental results have shown that our algorithm is much faster than CPU based one.

AB - In this paper we present a new novel GPU-based algorithm for real time object segmentation by employing several techniques which make use of framebuffer, Swizzle operator, stencil buffer and the other factors on GPU. Frame buffer is used for the fast processing of image on GPU without going back and forth to the CPU, swizzle operator for the efficient and fast execution of vector operations for object segmentation, and stencil buffer for the fast computation of the masked area for the detected object, thus speeding up the whole algorithm sharply. Moreover, the computation of the histograms and bounding boxes make our algorithm very simple and fast by using 'gather' operation uniquely supported by GPU. Our experimental results have shown that our algorithm is much faster than CPU based one.

UR - http://www.scopus.com/inward/record.url?scp=38549116525&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38549116525&partnerID=8YFLogxK

U2 - 10.1109/ICCIAS.2006.294232

DO - 10.1109/ICCIAS.2006.294232

M3 - Conference contribution

AN - SCOPUS:38549116525

SN - 1424406056

SN - 9781424406050

VL - 1

SP - 739

EP - 742

BT - 2006 International Conference on Computational Intelligence and Security, ICCIAS 2006

ER -