Scene Matching Algorithm Evaluation Based on Multi-core Parallel Computing Technology

Author

Li, Ni ; Gong, Guanghong ; Peng, Xiaoyuan ; Chen, Zheng

Author_Institution

Dept of Autom. Sci. & Electr. Eng., Beijing Univ. of Aeronaut. & Astronaut., Beijing, China

Volume

1

fYear

2009

fDate

19-21 May 2009

Firstpage

94

Lastpage

98

Abstract

Application of multi-core parallel computing technology in modeling and simulation field can promote effective schedule of multi-core computing resources. A scene matching simulation platform was built to evaluate computation efficiency of different algorithm implementation schemes. Users can select different preprocessing and matching algorithms from algorithm library and configure different algorithm parameters. Two kinds of typical multi-core computing technologies, which are OpenMP and TBB, are applied here to realize different algorithms. Simulation experiment results show that computing resources can be used more effectively and simulation efficiency of the evaluation platform can be greatly improved.

Keywords

application program interfaces; image matching; natural scenes; parallel processing; OpenMP technology; TBB technology; modeling-simulation field; multicore parallel computing technology; scene matching algorithm evaluation; Computational modeling; Computer architecture; Distributed computing; Layout; Object oriented modeling; Parallel processing; Runtime; Scheduling; Space technology; Yarn; multi-core; parallel computing; scene matching; simulation evaluation;

fLanguage

English

Publisher

ieee

Conference_Titel

Software Engineering, 2009. WCSE '09. WRI World Congress on

Conference_Location

Xiamen

Print_ISBN

978-0-7695-3570-8

Type

conf

DOI

10.1109/WCSE.2009.14

Filename

5318960