基于卡尔曼滤波器的Mean Shift行人跟踪算法  

Mean Shift Pedestrian Tracking Algorithm Based on Kalman Filter

作　　者：李印[1] Li Yin(Department of Electrical Engineering,Yingkou Institute of Technology,Yingkou 115014,China)

机构地区：[1]营口理工学院电气工程系,辽宁营口115014

出　　处：《湘南学院学报》2017年第5期18-21,78,共5页Journal of Xiangnan University

摘　　要：将卡尔曼滤波器和Mean Shift跟踪算法相结合,构建了一种改进的行人跟踪算法.首先利用卡尔曼滤波器预测跟踪行人的目标位置,用预测的中心位置作为Mean Shift跟踪向量移动的初始值,然后进行迭代,最终找到准确的跟踪位置.从车载视频中截取的图片作为实验依据,用MATLAB编程.实验结果显示,改进的算法能实现良好的跟踪效果.In this paper,we combine Kalman filter and Mean Shift tracking algorithm to construct an improved pedestrian tracking algorithm.Firstly,Kalman filter is used to predict the target position of tracking pedestrian,and the center of prediction is used as initial value of Mean Shift to track the initial movement of vector.And then it is analyzed by iterative,and ultimately the axact location of the track is found.The screenshots from the vehicle borne video is taken as experimental basis.The experimental results show that the improved algorithm can achieve good tracking effect.

关 键 词：卡尔曼滤波器 Mean SHIFT 行人跟踪 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]