基于卡尔曼滤波和SIFT特征的运动目标跟踪
刘兰英;路红
【期刊名称】《电子测试》 【年(卷),期】2013(000)024
【摘要】基于图像处理技术的交通监控系统能实时反应道路状况和车流信息,系统使用和维护费用相对较低,可广泛应用于路况复杂区域和交叉道口的监控。本文提出了一种基于卡尔曼滤波的多特征匹配的运动目标跟踪。该方法首先基于高斯差分图像金字塔提取出目标的SIFT特征点,根据该特征点在图像中进行目标检测,获取目标中心,再根据目标在下一帧的卡尔曼位置设置预测区域,在该搜索区域内结合目标中心和SIFT特征选取最匹配的目标进行跟踪,同时以该位置作为观测值,对卡尔曼滤波参数进行优化。实验结果表明,该算法在目标发生大尺度旋转和缩放、部分遮挡时能够稳定跟踪,并且具有较好的实时性和鲁棒性。%Traffic surveillance system based on image processing technology can reflect the information of road and traffic.The cost of use and maintenance is relatively low,which can be widely applied to monitor complex area and crossing the road. In this paper,a new algorithm for target tracking hadbe proposed,which is combine the SIFT algorithm with kalman filter.Firstly,extracting SIFT targets based on the Pyramid of Gauss difference image,target position was doped out by kalman filter to build the adapted window. Finally,the SIFT algorithm was used to extract target features and matching them.Experimental results showed that this method had strong robustness and realtime to