基于DSP利用粒子滤波算法实现目标跟踪  

Particle filter algorithm for target tracking based on DSP

作　　者：李雁斌[1] 曹作良[1] 刘常杰[1] 叶声华[1] 

机构地区：[1]天津大学精密测试技术及仪器国家重点实验室,天津300072

出　　处：《光电子．激光》2009年第6期771-774,共4页Journal of Optoelectronics·Laser

基　　金：国家"863"计划资助项目(2007AA04Z229);国际科技合作资助项目(2006DFA12410)

摘　　要：以TMS320DM643数字信号处理器(DSP)为核心,构建了高性能的视频处理平台,并利用该硬件平台实现粒子滤波(PF)算法完成对目标的跟踪。介绍了视频处理平台的基本结构和核心器件,并阐述了DSP实现运动目标跟踪的软件设计。实验表明,该系统能够实时跟踪目标,且相对于传统的图像采集卡与计算机结合的处理系统,具有体积小、低功耗、模块化和移动性好的特点,容易集成到各种移动设备中实现自主导航、安防监控等功能。A high-performance video processing platform is built on TMS320DM643 DSP, and target tracking is achieved based on particle filter. The basic structure and core devices of the video processing platform are introduced and the software design of object tracking is described. The experiments show that the system realizes real-time target tracking. Compared with the traditional processing system that combines image acquisition card with the computer, the system features compactness,low power,modularity and mobility. It also can be easily integrated into a variety of mobile devices to achieve autonomous navigation, security monitoring function, etc.

关 键 词：粒子滤波(PF) 数字信号处理器(DSP) 目标跟踪 

分 类 号：TN247[电子电信—物理电子学]