摘要
车辆跟踪是智能交通系统中的一项关键技术。文章在研究现有的车辆跟踪算法基础上,提出了一种基于卡尔曼(Kalman)与尺度不变特征变换(Scale invariant feature transform,SIFT)的车辆跟踪算法。通过将车辆的外接矩形信息转化为Kalman滤波参数,对车辆运动进行建模,结合SIFT特征匹配能够有效地解决车辆遮挡问题。实验结果表明,该方法能够对运动车辆实现稳定的跟踪,并且能够有效地解决车辆遮挡问题。
Vehicle tracking is one of the key technologies in Intelligent Transportation System. In this pa per, a new vehicle tracking algorithm based on Kalman and SIFT is proposed after researching of the existing algorithm. Vehicle moving model is made by converting the parameters of the contourrectangles to the parame ters of Kalman filter. Objects sheltering can be effectively resolved through matching SIFT feature. The experi ments demonstrate that vehicles can be tracked stably, and objects sheltering can be effectively resolved.
出处
《信息化研究》
2012年第4期14-17,49,共5页
INFORMATIZATION RESEARCH
基金
国家自然科学基金项目(No:60872073
No:60975017
No:51075068)
教育部博士点专项基金(No:20110092130004)
江苏省高校自然科学基金资助项目(NO:10KJB510005)
