基于视频的车辆检测和分析算法  

Detection and Tracking of Vehicles and Event Analysis from Video

作　　者：林海涵[1] 唐慧明[1] 

机构地区：[1]浙江大学信息科学与工程学院,浙江杭州310027

出　　处：《江南大学学报（自然科学版）》2007年第3期323-326,共4页Joural of Jiangnan University (Natural Science Edition)　

摘　　要：为了高速公路行车安全,需要及时检测公路上车辆的异常停车情况.通过对视频图像分析,首先重建背景图像,再分割出车辆目标,然后进行目标跟踪,采用基于针孔模型的摄像机定标估算车辆的速度,利用速度信息分析高速公路上的车辆停车事件.现场实验结果表明,此方法对于高速公路上异常停车的检测具有较高的准确性.Video-based surveillance systems have a wide range of applications for traffic monitoring. In this paper, an approach for the detection and tracking of vehicles in highway was proposed. The background is recovered from the video sequence. Firstly, then. vehicle object is extracted from the input images, speed of vehicle objects are estimated by means of tracking and camera calibration. Based on the speed and location, the stopping vehicles can be found. The experimental results from highway scenes demonstrate the feasibility and effectiveness of the method.

关 键 词：智能交通 车辆检测 目标跟踪 事件分析 

分 类 号：TN941.1[电子电信—信号与信息处理]