基于自适应卡尔曼滤波的运动车辆检测
首发时间:2008-06-27
摘要:卡尔曼滤波是一种根据时变随机信号的统计特性,对信号的未来值做出尽可能接近真值的一种估计方法,首先介绍了卡尔曼滤波原理,然后阐述了它在运动目标检测的应用。针对传统的固定值的卡尔曼滤波方法的缺陷,提出了自适应更新参数的卡尔曼滤波方法。通过与传统的卡尔曼滤波方法、帧差法、光流法和高斯混合模型方法的比较,证明了该方法的有效性。
For information in English, please click here
Moving Vehicle Detection Based on Adaptive Kalman Filter
Abstract:Kalman Filter is a method to estimate the future state of a process based on the statistic character of temporal process,in a way that minimizes the mean of the squared error. The paper introduced the Kalman Filter theory firstly, then presented the application of the moving vehicle detection。For the improvement of traditional Kalman Filter, the adaptive updating parameters was proposed,. Compared to traditional Kalman Filter, temporal difference method , Optical Flow method and Gaussian Mixture Model, the experiments show that the method is effective.
Keywords: Adaptive Kalman Filter; Background Updating; Vehicle Detection
基金:
论文图表:
引用
No.2253627142612145****
同行评议
共计0人参与
勘误表
基于自适应卡尔曼滤波的运动车辆检测
评论
全部评论0/1000