Title :
A Study on Data Parallel Optimization for Real-time Vehicle Recognition Algorithm
Author :
Yang, Chunyang ; Wen, Xuezhi ; Yuan, Huai ; Duan, Bobo
Author_Institution :
Northeastern Univ., Shenyang
fDate :
Sept. 30 2007-Oct. 3 2007
Abstract :
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.
Keywords :
computer vision; image classification; motion estimation; object recognition; optimisation; parallel algorithms; real-time systems; road vehicles; data parallel optimization; image classifier; image filters; image motion estimation; vision based real-time vehicle recognition algorithm; Algorithm design and analysis; Computer vision; Concurrent computing; Hardware; Image processing; Intelligent transportation systems; Intelligent vehicles; Machine learning algorithms; Optimization methods; Parallel processing;
Conference_Titel :
Intelligent Transportation Systems Conference, 2007. ITSC 2007. IEEE
Conference_Location :
Seattle, WA
Print_ISBN :
978-1-4244-1396-6
Electronic_ISBN :
978-1-4244-1396-6
DOI :
10.1109/ITSC.2007.4357774
