Efficient Implementation of Canny Edge Detection Filter for ITK Using CUDA

Author

Lourenço, Luis H A ; Weingaertner, Daniel ; Todt, Eduardo

Author_Institution

Inf. Dept., Univ. Fed. do Parana, Curitiba, Brazil

fYear

2012

fDate

17-19 Oct. 2012

Firstpage

33

Lastpage

40

Abstract

This work presents an efficient CUDA implementation of the Canny edge detection Filter for the Insight Segmentation and Registration Toolkit (ITK). The algorithm is tested on three generations of NVidia GPGPUs, showing performance gains of 3.6 to 50 times when compared to the standard ITK Canny running on two CPU models. The CUDA-enabled Canny is also compared to a more efficient Canny implementation from the OpenCV library. Examples of coding strategies to avoid warp serialization in CUDA are shown on a smart implementation of the Sobel filter, as well as on other algorithms.

Keywords

edge detection; filtering theory; graphics processing units; image coding; image registration; image segmentation; parallel architectures; CUDA; Canny edge detection filter; ITK toolkit; Insight segmentation and registration toolkit; Nvidia GPGPU; OpenCV library; Sobel filter; coding strategy; compute unified device architecture; general-purpose graphics processing unit; warp serialization; Graphics processing units; Hardware; Hysteresis; Image edge detection; Instruction sets; Kernel; CUDA; Canny; Gaussian filter; ITK; Sobel; edge detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Systems (WSCAD-SSC), 2012 13th Symposium on

Conference_Location

Petropolis

Print_ISBN

978-1-4673-4468-5

Type

conf

DOI

10.1109/WSCAD-SSC.2012.21

Filename

6391761