By Topic

A Study on Data Parallel Optimization for Real-time Vehicle Recognition Algorithm

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Chunyang Yang ; Software Center, Northeastern University, Shenyang 110004, China, yangcy@neusoft.com ; Xuezhi Wen ; Huai Yuan ; Bobo Duan

Data parallelization is an important method for speed up the vision based vehicle recognition system. And with the risen of multi/many cores, new programmability has been introduced to extend its ability to express more complicated and irregular algorithm utilizing multi/many cores hardware, this paper presents our study on data parallel computation model and illustrates our prime data parallel optimization for the key algorithms of vision based vehicle recognition algorithm including image filters, classifier and motion estimation. And after analyzing the result of optimization, the applicably bound of data parallel optimization and the future direction of parallel optimization for vision based vehicle recognition algorithm is summarized.

Published in:

2007 IEEE Intelligent Transportation Systems Conference

Date of Conference:

Sept. 30 2007-Oct. 3 2007