Parallel GPU Implementation of Hough Transform for Circles
Hough transform is one of the most widely used algorithms in image processing. The major problems of Houghs transform are its time consuming and its abundant requirement of computational resources. In this paper, we try to solve this problem by paralleling this algorithm and implementing it on GPUs(Graphic Process unit) using CUDA(Compute Unified Device Architecture) . We have introduced two methods for parallelization, each of which has been implemented on four different graphic cards using CUDA. After executing the proposed methods on GPUs, we have compared our results with sequential algorithm execution on CPU and it is observable that we have about 65 times more speedup toward the sequential algorithm.
Keywords: CUDA, Hough Transform, Image Processing, Parallel algorithm, GPU.
Download Full-Text
ABOUT THE AUTHORS
Meisam Askari
Department of Computer Engineering, University of Kashan Kashan, Iran
Hossein Ebrahimpour
Department of Computer Engineering, University of Kashan Kashan, Iran
Azam Asilian Bidgoli
Faculty of Electronic and Computer Engineering, Pooyesh Higher Education Institute Qom, Iran
Farahnaz Hosseini
Department of Computer Engineering, University of Kashan Kashan, Iran
Meisam Askari
Department of Computer Engineering, University of Kashan Kashan, Iran
Hossein Ebrahimpour
Department of Computer Engineering, University of Kashan Kashan, Iran
Azam Asilian Bidgoli
Faculty of Electronic and Computer Engineering, Pooyesh Higher Education Institute Qom, Iran
Farahnaz Hosseini
Department of Computer Engineering, University of Kashan Kashan, Iran