Title: GPU accelerated real time rotation, scale and translation invariant image registration method
Authors: Sah, Sudkahar
Vaněk, Jan
Roh, YoungJun
Wasnik, Ratul
Citation: SAD, Sudkahar; VANĚK, Jan; ROH, YoungJun; WASNIK, Ratul. GPU accelerated real time rotation, scale and translation invariant image registration method. In: International conference on image analysis and recognition. Berlin: Springer, 2012, p. 224-233. (Lecture notes in computer science; 7324). ISBN 978-3-642-31294-6.
Issue Date: 2012
Publisher: Springer
Document type: článek
URI: http://www.kky.zcu.cz/cs/publications/SudhakarSah_2012_GPUAcceleratedReal
ISBN: 978-3-642-31294-6
Keywords: GPU;registrace obrazu;CUDA;OpenCL;rozpoznávání objektů
Keywords in different language: GPU;image registration;CUDA;OpenCL;object recognition
Abstract in different language: This paper presents highly optimized implementation of image registration method that is invariant to rotation scale and translation. Image registration method using FFT works with comparable accuracy as similar methods proposed in the literature, but practical applications seldom use this technique because of high computational requirement. However, this method is highly parallelizable and offloading it to the commodity graphics cards increases its performance drastically. We are proposing the parallel implementation of FFT based registration method on CUDA and OpenCL. Performance analysis of this implementation suggests that the parallel version can be used for real time image registration even for image size up to 2k x 2k. We have achieved significant speed up of up to 345x on NVIDIA GTX 580 using CUDA and up to 116x on AMD HD 6950 using OpenCL. Comparison of our implementation with other GPU based registration method reveals that our implementation performs better compared to other implementations.
Rights: © Sudhakar Sah - Jan Vaněk - YoungJun Roh - Ratul Wasnik
Appears in Collections:Články / Articles (KIV)

Files in This Item:
File Description SizeFormat 
SudhakarSah_2012_GPUAcceleratedReal.pdfPlný text699 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/16979

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