基于TMS320DM642的实时运动目标检测与跟踪系统  

Real-time Motion Target Detecting and Tracking System Based on TMS320DM642

作　　者：贾茜[1] 谢勤岚[1] 董蓓[1] 

机构地区：[1]中南民族大学电信学院,湖北武汉430074

出　　处：《计算机测量与控制》2009年第3期469-471,共3页Computer Measurement &Control

基　　金：国家自然科学基金资助项目(40774089);中南民族大学自然科学基金项目(YZY04009)

摘　　要：CAMShift算法凭借其良好的实时性和鲁棒性而计算量小,在目标跟踪邻域占有重要地位;而单纯的CAMShift是一种需要人预先对目标进行识别和判断以获得目标颜色模式的半自动跟踪器;文章采取帧差法和CAMShift算法相结合的方法,设计了一种自动的运动目标检测与跟踪系统;该系统首先用时间连续的三帧双差分对运动目标的识别和提取,自动地选取搜索窗;再通过CAMShift算法计算目标的精确位置并调整搜索窗口大小;最后通过串口发送云台控制信息,驱动云台运动使目标始终保持在视场之内;在以DM642为核心的硬件平台上,实现了系统的软件算法;实验表明在对比度较高时,无人为干预的情况下,系统能有效、实时地跟踪目标。For the superior tracking performanee of real--time and robustness obtained with low computational complexity, CAMShift Algorithm is of great importance in video tracking. It＇s a semi--automatic tracker, however, which is in need of judging and reeognizing target by human. In this paper, an automatic tracking system has been designed by the means of combining differencing--frame and CAMShift. Firstly, foreground ／ background is deteeted through sequential double-- differencing--three--frame. The CAMShift Algorithm is then used to ealeulate the exact location of the target and adjust the size of search window. The location information is transformed into the characters and sent via the serial port lastly, to control the PTZ for maintaining the target being always visible in the scene. The software algorithm has been implemented on the hardware with the core of DM642. Our experimental results show that, the system is efficient as a video tracker without human under high contrast environment.

关 键 词：TMS320DM642 运动目标自动检测与跟踪 CAMSHIFT 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]