基于视频的车辆检测与跟踪算法综述  

Survey on Video Based Vehicle Detection and Tracking Algorithms

作　　者：董春利[1,2] 董育宁[1,3] 

机构地区：[1]南京邮电大学通信与信息工程学院,江苏南京210003 [2]南京交通职业技术学院信息工程系,江苏南京211188 [3]苏州大学江苏省计算机信息处理技术重点实验室,江苏苏州215006

出　　处：《南京邮电大学学报（自然科学版）》2009年第2期88-94,共7页Journal of Nanjing University of Posts and Telecommunications：Natural Science Edition

基　　金：教育部科学技术研究重点项目(205060);江苏省高校自然科学重大基础研究项目(07KJA51006);苏州大学江苏省计算机信息处理技术重点实验室开放课题(KJS0712);华为公司科技基金资助项目

摘　　要：首先介绍了交通检测系统,指出视频交通检测技术日益成为计算机视觉领域中备受关注的前沿方向。在此基础上,分别讨论了常用的车辆检测算法,基于模型的车辆检测算法,车辆跟踪的基本类型,以及基于模板匹配、卡尔曼滤波和粒子滤波的车辆跟踪算法,同时分析比较了各种算法的优缺点。最后,展望了这一领域未来研究的热点。The traffic detection system is introduced first ,and it is pointed out that the video based traffic detection technique is increasingly becoming the most active research topics in the field of computer vision. Then various algorithms are discussed respectively, such as the commonly used vehicle detection algorithms, the model based vehicle detection algorithms, the basic types of vehicle tracking, as well as the template matching, Kalman filtering and Particle filtering based vehicle tracking algorithms. The advantages and disadvantages of various algorithms are compared in detail. Finally, the hot spots for future research in this area are presented.

关 键 词：智能交通系统 交通检测系统 车辆检测 车辆跟踪 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]