实时车辆检测和跟踪系统设计  

The Design of Real-Time Vehicle Detection and Tracking System

作　　者：王晓东[1] 丁冬花[1] 

机构地区：[1]清华大学计算机科学与技术系

出　　处：《微计算机信息》2006年第11Z期237-239,共3页Control & Automation

基　　金：国家"863"项目(2002AA420110-3)

摘　　要：实时车辆检测和跟踪是室外移动机器人尤其是智能汽车研究领域的一个重要课题。本文介绍了多功能室外移动机器人THMR-V的实时车辆检测和跟踪系统。该系统包括车道线检测和车辆检测和跟踪两个主要模块。车道线检测算法使用新的搜索策略,实时检测结构化道路区域,减少车辆检测算法搜索范围。车辆检测算法以Adaboost算法为基础,利用边缘方向特征,颜色特征,和对称性特征实现车辆检测。文中详细介绍了系统的实现。Vehicle Detection is one of the most important subjects in the field of outdoor mobile robot especially intelligent car. The real-time vehicle detection and tracking system on THMR-V, a muhifunctional intelligent outdoor mobile robot, is introduced. The system consists of two major components. Lane dtection algorithm utilizes a noval search method, detecing road region and reduing search area. Vehicle detection algorithm based on Adaboost algorithm uses many important features , such as edge orientation fea- tures, color features and symmetry features. The realization of the system is presented in detail.

关 键 词：移动机器人 车辆检测 分类器 车辆跟踪 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]