首页 | 官方网站   微博 | 高级检索  
     

运动像机下基于粒子滤波的多目标跟踪算法
引用本文:陆意骏,陈一民,黄诗华.运动像机下基于粒子滤波的多目标跟踪算法[J].计算机工程与设计,2010,31(7).
作者姓名:陆意骏  陈一民  黄诗华
作者单位:上海大学计算机工程与科学学院,上海,200072
基金项目:国家科技支撑计划课题基金,上海市重点学科建设基金 
摘    要:针对摄像机运动情况下的多目标跟踪问题,提出了基于粒子滤波的跟踪算法.在粒子滤波算法基础上,将二阶自回归过程作为系统状态转移模型,HSV颜色直方图作为观测模型,对视频中多个目标的位置、大小进行跟踪.实验结果表明,该算法能实时正确地跟踪多个目标,并对局部遮挡有较好的鲁棒性,也能在目标短暂消失导致跟踪失败后,在目标重新出现后及时捕获并继续进行跟踪.

关 键 词:多目标跟踪  摄像机运动  粒子滤波  自回归过程  HSV颜色直方图

Multi-target tracking algorithm of moving camera video based on particle filter
LU Yi-jun,CHEN Yi-min,HUANG Shi-hua.Multi-target tracking algorithm of moving camera video based on particle filter[J].Computer Engineering and Design,2010,31(7).
Authors:LU Yi-jun  CHEN Yi-min  HUANG Shi-hua
Affiliation:LU Yi-jun,CHEN Yi-min,HUANG Shi-hua(School of Computer Engineering , Science,Shanghai University,Shanghai 200072,China)
Abstract:A tracking algorithm based on particle filter is proposed to deal with multi-target tracking in a camera motion situation.In the proposed algorithm,the position and scale of targets in the video are tracked by using a second-order auto-regressive process as the tran-sition model and an HSV histogram as the observation model.Experimental results show that the proposed algorithm can track multi-target correctly in real-time and is robust to the partial occlusion.In addition,it can recover from tracking failur...
Keywords:multi-target tracking  camera motion  particle filter  auto-regressive process  HSV histogram
本文献已被 CNKI 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-23

京公网安备 11010802026262号