摘要
在视频车辆跟踪算法中针对传统粒子滤波的非线性、非高斯性可能导致跟踪过程的不准确性,提出一种基于Mean-Shift的卡尔曼(Kalman)粒子滤波算法。该算法利用建立基于目标颜色直方图特征模型对视频车辆目标进行建模,并将其与Kalman滤波相结合进行更新;通过采用Mean Shift算法将Kalman滤波器引用到粒子滤波器当中,通过预测迭代,从而达到对车辆的运行轨迹的修正。将先验信息预测与粒子滤波相结合在保持跟踪系统整体上的非线性、非高斯性,兼顾了卡尔曼滤波局部的线性高斯特性。实验结果表明,该方法与传统粒子滤波方法相比,具有较好的实时性和较高的准确率,能够准确稳定地对目标车辆进行跟踪。
In video vehicle tracking algorithm, the nonlinear, non-Gaussian property in traditional particle filter may lead to inaccuracy in tracking process. This paper puts forward a mean-shift-based Kalman particle filter algorithm to solve this problem. The algorithm models the video vehicle target by making use of building the target eolour-based histogram feature model, and combines it with the Kalman filter for updating ; it also applies the Kalman filter to particle filter by using mean-shift algorithm, and achieves the correction of vehicle＇s moving track through prediction iteration. The method combines the priori information and the particle fihering on the overall nonlinear and non-Gaussian properties of the tracking system, and takes into account the local linear Gaussian feature of Kalman filter as well. Experimental result shows that this method has better real-time property and higher accuracy rate than the traditional particle filter methods, and is able to track the target vehicles accurately and stably.
出处
《计算机应用与软件》
CSCD
北大核心
2014年第9期236-239,252,共5页
Computer Applications and Software
基金
国家自然科学基金项目(51106070)
关键词
智能交通系统
车辆跟踪
均值漂移
粒子滤波
卡尔曼滤波器
Intelligent transportationsystem
Vehicle tracking
Mean-shift
Particle filter
Kalman filter
