一种基于特征的多目标跟踪算法  

A Method of Multi-object Tracking Based on Feature

作　　者：付晓薇[1] 方康玲[1] 李曦[2] 

机构地区：[1]武汉科技大学信息学院,武汉430081 [2]上海交通大学信息学院,上海200030

出　　处：《计算机工程与应用》2004年第35期72-74,共3页Computer Engineering and Applications

摘　　要：论文提出了一种基于特征的多目标跟踪算法。根据目标在相邻帧间运动具有连续性,并且包围窗口、灰度变化不大的特点,该算法改进了一种代价函数。在跟踪的匹配过程中,启动了卡尔曼滤波,预测目标匹配搜索区域。同时,使用目标链记录了目标最新的运动状态和特征值,保证了运动跟踪的连续性。This paper proposes a method of multi-object tracking based on feature.Regarding of the moving continuity and the small change of object's features in frames,a kind of cost function is put forward in the tracking algorithm,which is applied in the tracking match of the image.At the same time ,the Kalman filter is used to predicate the search areas of the matching objects,and then,moving state and feature value of the objects in current frame are recorded to ensure the continuity of the dynamic tracking depended on the object-chain.

关 键 词：动态图像 多目标跟踪算法 目标链 卡尔曼滤波 图像处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]