| 基于粒子滤波的目标实时跟踪系统 |
| |
| 引用本文： | 孙俊喜,孙中森,宋建中. 基于粒子滤波的目标实时跟踪系统[J]. 电视技术, 2007, 31(3): 85-87 |
| |
| 作者姓名： | 孙俊喜 孙中森 宋建中 |
| |
| 作者单位： | 中国科学院长春光学精密机械与物理研究所,吉林,长春,130033;中国科学院研究生院,北京,100039;中国科学院长春光学精密机械与物理研究所,吉林,长春,130033 |
| |
| 摘 要： | 设计一种基于TMS320VC5416与FPGA的实时图像跟踪系统,该系统首先采用SAA7111A采集图像,经FPGA(采用乒乓操作的方式)传输给DSP处理器.在跟踪算法上采用灰度作为目标特征,使用粒子滤波方法实现对动态目标的跟踪.采用浮点数定点化处理,提高了算法的运行速度.实验表明:该系统具有良好的实时性与稳定性.
|
| 关 键 词： | 实时跟踪 粒子滤波 模板匹配 |
| 文章编号： | 1002-8692(2007)03-0085-03 |
| 修稿时间： | 2007-01-08 |
An Object-Tracking System Using Particle Filter |
| |
| SUN Jun-xi,SUN Zhong-sen,SONG Jian-zhong. An Object-Tracking System Using Particle Filter[J]. Ideo Engineering, 2007, 31(3): 85-87 |
| |
| Authors: | SUN Jun-xi SUN Zhong-sen SONG Jian-zhong |
| |
| Affiliation: | 1, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China; 2, Graduate School of the Chinese Academy of Sciences, Beijing 100039, China |
| |
| Abstract: | Based on TMS320C5416 and FPGA, a practical system for tracking of target using particle filter is presented. The original image is firstly sampled by SAA7111A, and then transmitted to DSP by Ping-Pang Method via FPGA. The gray feature is selected as the object characteristic and particle filter is used for object tracking. Fixed-point operation is used instead of floating-point operation for increasing the speed of computation. Experimental results show that the system operates well in real-time and is robust. |
| |
| Keywords: | real-time tracking particle filter template matching |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
