Parallized Pipeline for Vehicle Detection
OpenMP is usually applied to the problems that are essentially part serial, meaning that these problems must be performed as a sequence step. Therefore, it can parallelize the , function code that performs in the sequential execution order. In this paper, we propose and apply two parallized pipelines based OpenMP to the video vehicle tracking program and run the programs in symmetric multiprocessor. Compared with serial counterpart, the results showed the realtime performance of parallelized vehicle tracking programs had been greatly improved. This paper also discusses the issues must be encountered in pipeline to improve the system performance.
parallel computing pipeline vehicle detection OpenMP
Zhong Huang Yijian Pei Hao Wu
School of Information Science and Engineering, Yunnan University, No. 2, North Green Lake Road Kunming, P.R.China, 650091
国际会议
2010 International Conference on Software and Computing Technology(2010年软件与计算机技术国际会议 ICSCT 2010)
昆明
英文
388-391
2010-10-17(万方平台首次上网日期,不代表论文的发表时间)