首页 | 本学科首页   官方微博 | 高级检索  
     

一种尺度自适应的粒子滤波跟踪算法
引用本文:师改梅,周建雄,张笑微,彭定明,万妍. 一种尺度自适应的粒子滤波跟踪算法[J]. 电视技术, 2009, 33(1)
作者姓名:师改梅  周建雄  张笑微  彭定明  万妍
作者单位:西南科技大学,信息工程学院,四川,绵阳,621010;中国兵器工业部第58研究所,军品部,四川,绵阳,621000
基金项目:四川省教育厅重点项目,国防基础科研项目 
摘    要:针对复杂背景下目标发生旋转、遮挡、尺度变化和摄像机运动时不能实时跟踪到目标的问题,将最佳核窗宽方法和信息量度量方法相结合,用于粒子滤波框架中.各个粒子通过均值偏移来搜索峰值,同时加入了相应的遮挡策略.实验结果表明,该算法在目标发生旋转、遮挡后仍能很好地跟踪到目标.同时跟踪窗能随目标尺度的大小变化作相应调整,大大提高了算法的实时性和稳健性.

关 键 词:遮挡  尺度变化  信息度量  粒子滤波  均值偏移算法

Scale Adaptive Particle Filter Tracking Method
SHI Gai-mei,ZHOU Jian-xiong,ZHANG Xiao-wei,PENG Ding-ming,WAN Yan. Scale Adaptive Particle Filter Tracking Method[J]. Ideo Engineering, 2009, 33(1)
Authors:SHI Gai-mei  ZHOU Jian-xiong  ZHANG Xiao-wei  PENG Ding-ming  WAN Yan
Affiliation:1.School of Information Engineering;Southwest University of Science and Technology;Sichuan Mianyang 621010;China;2.Dept.of Armament Products;No.58 Research Institute of China Ordnance Industry;Sichuan Mianyang 621000;China
Abstract:Robust real-time object tracking is the critical task while there are rotation, occlusions, target scale variations and camera motion.It presents the information measure into particle filtering, which has typically been used in combination with best bandwidth.The proposed tracker first produces a few of samples and then shifts the samples toward a close local maximum using Mean-Shift, while multiple hypotheses are processed in cases of occlusion.In the presented tracking examples, the improved algorithm can...
Keywords:occusion  scale variations  information measure  particle filter  Mean-Shift algorithm  
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