一种尺度自适应的核相关滤波跟踪算法  

Scale adaptive kernelized correlation filter tracking method

作　　者：林庆[1] 占林森 LIN Qing;ZHAN Lin-sen(School of Computer Science and Communication Engineering,Jiangsu University,Zhenjiang 212013,Jiangsu Province,China)

机构地区：[1]江苏大学计算机科学与通信工程学院,江苏镇江212013

出　　处：《信息技术》2018年第9期146-150,共5页Information Technology

摘　　要：针对常规的相关滤波跟踪算法在有尺度变化的目标跟踪中存在的不足,提出了一种自适应尺度的相关滤波跟踪算法。改进的方法在核相关滤波跟踪算法中引入信息量度量方法来表示目标尺度的变化情况,接着根据相邻两帧图像的相似度来调整学习因子更新分类器。实验结果表明,改进的方法能更好地提高跟踪精度。Since the conventional correlation filter tracking algorithm has poor performance in tracking object with scale variation, a scale adaptive correlation filter tracking algorithm is proposed. The information measure method is introduced to represent the change of target scale in the proposed method.Then,the learning rate of classifier is piece-wisely adjusted according to the similarity of two adjacent frames. The experimental results show that the improved method has better performance in target tracking.

关 键 词：相关滤波器 尺度自适应 信息量度量 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]