机构地区: 华南理工大学计算机科学与工程学院
出 处: 《计算机工程与应用》 2008年第34期239-242,共4页
摘 要: 提出了一种基于粒子滤波视频跟踪算法的停车事件检测方法,实现了对高速公路交通视频的自动监控。首先用混合差分技术,快速提取出视频中的车辆对象;并用粒子滤波算法实现了运动车辆的跟踪;进而通过对车辆运动的数学建模,对停车事件进行了自动检测。最后,对多组高速公路交通视频进行测试,结果表明:提出的检测方法比其他常用方法响应速度更快,且具有较高的检测准确率和鲁棒性。 A method of vehicle breaking detection based on particle filter is proposed,for automatic detection of traffic video on express way.A hybrid difference approach is used to obtain the vehicle objects of video.An improved particle filter algorithm is designed for tracking the vehicle of the video.The mathematic model of moving and breaking behavior of the tracking vehicle is given for detecting.Finally,several traffic videos are tested,and the results indicate the proposed method is efficient,high-detection-rate and robust.
领 域: [自动化与计算机技术] [自动化与计算机技术]