Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

GPU-based Barrel Distortion Correction for Acceleration

Authors
Luo ShuhuaJun, Zhang
Issue Date
Nov-2013
Publisher
IEEE
Keywords
geometric correction; barrel distortion; GPU; radial distortion
Citation
2013 IEEE 10th International Conference on High Performance Computing and Communications & 2013 IEEE International Conference on Embedded and Ubiquitous Computing, pp 845 - 848
Pages
4
Indexed
SCOPUS
Journal Title
2013 IEEE 10th International Conference on High Performance Computing and Communications & 2013 IEEE International Conference on Embedded and Ubiquitous Computing
Start Page
845
End Page
848
URI
https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/115868
DOI
10.1109/HPCC.and.EUC.2013.121
Abstract
Geometric correction is a practical and effective barrel distortion correction method. It mainly consists of two stages: the first stage is to take coordinates mapping from distortion image to correction image; the second stage is bilinear interpolation. It involves a certain amount of calculation, and the larger the image is, the more the quantity of calculation is. What's more, the processing speed of geometric correction implemented on central processing unit (CPU) can't meet the need of high-speed in real-time application fields. Compared with serial processing pipeline of CPU, graphics processing unit (GPU) has special parallel processing pipeline which is suitable and fast for mass data calculation in parallel. Therefore, it can provide an implementation of geometric correction on GPU with considerable acceleration effect. The paper proposes an implementation of geometric correction on GPU by using open graphics library (OpenGL) and graphics library shading language (GLSL) for portability. The experiment results show that the full execution performance of the implementation on GPU is over 190 times speedup of that completely on CPU at most, which obtains a high-speed processing effect.
Files in This Item
Appears in
Collections
COLLEGE OF ENGINEERING SCIENCES > SCHOOL OF ELECTRICAL ENGINEERING > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher ZHANG, Jun photo

ZHANG, Jun
ERICA 공학대학 (SCHOOL OF ELECTRICAL ENGINEERING)
Read more

Altmetrics

Total Views & Downloads

BROWSE