全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于信噪比最大化的目标自适应跟踪

DOI: 10.11834/jig.20080116

Keywords: 关键词:自适应特征模型,信噪比,目标跟踪,mean,shift

Full-Text   Cite this paper   Add to My Lib

Abstract:

摘要:针对采用静态目标表达模型容易导致跟踪失败的缺点,本文提出一种基于自适应特征生成模型的目标跟踪方法。在该方法中,将目标看作为有效跟踪信号,而背景则为随机噪声,在对目标的似然图像进行构建后,采用局部信噪比对当前目标所处特征空间的可跟踪性进行量化比较,选用信噪比最大的表达模型作为当前的特征跟踪模型。基于MeanShift的目标跟踪实验表明,与采用静态目标表达模型相比,文中的算法具有更好的鲁棒性和可行性。

References

[1]  Collins R T,Liu Yan-xi,Leordeanu M.Online selection of discriminative tracking features[A].In:Proceedings of Ninth IEEE International Conference on Computer Vision[C],Nice,France,2003:346~352.
[2]  Wang Jian-yu,Chen Xi-lin,Gan Wen.Online selecting discriminative trucking features using particle filter[A].In:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C],San Diego,CA,USA,2005,2:1037~1042.
[3]  Bohyung Han,Davis L.Robust observations for object tracking[A].In:Proceedings of the 12th International Conference on Image Processing[C],Genoa,Italy,2005,2:442~445.
[4]  Fukunaga K,Hostetler L D.The estimation of the gradient of a density function,with applications in pattern recognition[J].IEEE Transactions on Information Theory,1975,21(1):32~40.
[5]  Comaniciu D,Meer P.Mean shift:A robust approach toward feature apace analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603~619.
[6]  Collins R T,Liu Yan-xi,Leordeano M.Online selection of discriminative tracking features[J].IEEE Transsctions on Pattern Analysis and Machine Intelligence,2005,27(10):1631~1643.
[7]  Bohyung Han,Davis L.Object tracking by adaptive feature extraction[A].In:Proceedings of the 11th International Conference on Image Processing[C],Singapore,2004,3:1501~1504.
[8]  Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564~577.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133