首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种基于特征代价函数的多目标跟踪算法
引用本文:付晓薇,方康玲,邱奕敏,李曦.一种基于特征代价函数的多目标跟踪算法[J].武汉科技大学学报(自然科学版),2004,27(4):416-418.
作者姓名:付晓薇  方康玲  邱奕敏  李曦
作者单位:1. 武汉科技大学,湖北,武汉,430081
2. 上海交通大学,上海,200030
摘    要:提出一种基于特征代价函数的多目标跟踪算法。根据目标在相邻帧间运动具有连续性以及包围窗口、灰度变化不大的特点,改进了一种代价函数。在跟踪的匹配过程中,启动卡尔曼滤波和预测目标匹配搜索区域,同时使用目标链记录目标最新的运动状态和特征值,从而保证运动跟踪的连续性和计数的有效性。

关 键 词:动态图像  跟踪  目标链  卡尔曼滤波
文章编号:1672-3090(2004)04-0416-03
修稿时间:2004年10月20

A Method of Multi-object Tracking Based on Cost Function of Features
FU Xiao-wei,FANG Kang-ling,QIU Yi-min,LI Xi.A Method of Multi-object Tracking Based on Cost Function of Features[J].Journal of Wuhan University of Science and Technology(Natural Science Edition),2004,27(4):416-418.
Authors:FU Xiao-wei  FANG Kang-ling  QIU Yi-min  LI Xi
Institution:FU Xiao-wei~1,FANG Kang-ling~1,QIU Yi-min~1,LI Xi~2
Abstract:This paper proposes a method of multi-object tracking based on cost function of features.In light of the moving continuity and the small change of object's features in frames, a kind of cost function is put forward for 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 moving state and feature value of the objects in current frame are recorded to ensure the continuity and effectiveness of the dynamic tracking by means of the object-chain.
Keywords:dynamic image  tracking  object-chain  Kalman filter  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号