A parallel mapping of optical flowto Compute Unified Device Architecture for motion-based image segmentation

Author

Kuchnio, Peter ; Capson, David W.

Author_Institution

Dept. of Electr. & Comput. Eng., McMaster Univ., Hamilton, ON, Canada

fYear

2009

fDate

7-10 Nov. 2009

Firstpage

2325

Lastpage

2328

Abstract

A correlation-based optical flow algorithm using compute unified device architecture (CUDA) technology to achieve fast motion-based image segmentation is described. Using CUDA, a 240 processor GPU implementation of an optimized correlation-based optical flow algorithm allows segmentation to be achieved at high frame rates on high-resolution video sequences. Details of the mapping of the optical flow segmentation algorithm onto the CUDA architecture as well as performance results are given. The performance of the algorithm is further characterized as a function of the search and correlation window radii.

Keywords

computer graphics; coprocessors; image motion analysis; image segmentation; image sequences; CUDA architecture; compute unified device architecture technology; correlation window radii; graphics processing units; high-resolution video sequences; motion-based image segmentation; optical flow parallel mapping; optical flow segmentation algorithm; optimized correlation-based optical flow algorithm; processor GPU; Biomedical optical imaging; Computer architecture; Concurrent computing; Graphics; Image motion analysis; Image segmentation; Optical computing; Optical devices; Optical noise; Yarn; CUDA; Motion-based Image Segmentation; Parallel Optical Flow Algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2009 16th IEEE International Conference on

Conference_Location

Cairo

ISSN

1522-4880

Print_ISBN

978-1-4244-5653-6

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2009.5414402

Filename

5414402