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

基于粒子滤波和Mean-shift的自适应目标跟踪方法
引用本文:陈小娟,佘二永.基于粒子滤波和Mean-shift的自适应目标跟踪方法[J].科学技术与工程,2013,13(33).
作者姓名:陈小娟  佘二永
作者单位:北京工商大学计算机与信息工程学,中国国防科技信息中心
摘    要:目标跟踪技术一直是计算机视觉的核心内容。本文结合粒子滤波与Mean-shift跟踪方法,提出了一种新的自适应目标跟踪方法,通过利用粒子滤波获取目标的初始位置,进而采用Mean-shift跟踪方法,实现目标跟踪的准确定位,同时,通过抑制背景特征分布,更新目标特征分布,从而在跟踪过程中自适应调整目标的模板表示。实验结果表明了本文提出方法的有效性。

关 键 词:粒子滤波  Mean-shift  目标跟踪    彩色直方图
收稿时间:7/4/2013 12:00:00 AM
修稿时间:2013/7/21 0:00:00

Adaptive Target Tracking Algorithm Based on Particle Filtering and Mean-shift
chenxiaojuan and She Eryong.Adaptive Target Tracking Algorithm Based on Particle Filtering and Mean-shift[J].Science Technology and Engineering,2013,13(33).
Authors:chenxiaojuan and She Eryong
Institution:China Defense Science and Technology Information Center
Abstract:Target tracking is an important topic in computer vision. In this paper, a new adaptive target tracking algorithm based on Particle Filtering and Mean-shift was proposed. The initial position of target was acquired by using Particle Filter, then the accurate position of target was finally obtained by using the Mean-shift method. At the same time, the target template representation was adaptive adjusted through the background characteristics suppression and the target characteristics updating. Experimental results demonstrate the effectiveness of the method.
Keywords:Particle Filtering  Mean-shift  Target Tracking  Color Histogram
点击此处可从《科学技术与工程》浏览原始摘要信息
点击此处可从《科学技术与工程》下载免费的PDF全文
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