摘要
该文提出了一种鲁棒的基于空间直方图的均值漂移目标跟踪算法。该算法首先用卡尔曼滤波(KF)预测目标在当前帧的位置,然后将预测结果作为改进的空间直方图的均值漂移目标跟踪算法的初值,用均值漂移算法搜索目标在当前帧的位置,同时更新KF算法的预测值。仿真实验表明该方法具有较好的跟踪精度,且对遮挡具有较强的鲁棒性。
This paper presents a robust mean shift object tracking algorithm based on spatial histogram. First, the center of the object predicted by KF is used as the initial value of the MS algorithm. Then the mean shift is used to search the object. The searching result of MS is fed back as the measurement of the KF to update the predicted value. The experimental results demonstratethat the proposed algorithm has good localization precision of tracking, and is robust against occlusion.
出处
《电脑知识与技术（过刊）》
2015年第5X期160-161 164,164,共3页
Computer Knowledge and Technology
基金
国家级大学生创新创业训练计划项目(201310705012)
