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SVM和AdaBoost的红外目标跟踪

DOI: 10.11834/jig.20071118

Keywords: 目标跟踪,AdaBoost,支持向量机,参数调整策略,均值漂移

Full-Text   Cite this paper   Add to My Lib

Abstract:

为了提高目标跟踪的鲁棒性,提出了一种新的用于红外目标跟踪的DABSVT算法。该算法首先把目标跟踪转化为目标和背景的两类分类问题,然后将根据每一帧的正负样本训练的支持向量机(SVM)作为分量分类器,并通过恰当的参数调整策略,利用AdaBoost算法把这些分量分类器组合成一个总体分类器;接着利用该总体分类器来区分下一帧中的目标和背景,并得到置信图;最后通过均值漂移算法找到置信图的峰值,得到目标的新位置。该新位置不仅与目标和背景的变化相适应,而且分量分类器可以随时加入或丢掉。实验结果显示,该方法是鲁棒的。

References

[1]  Bal A,Alam M S.Automatic target tracking in FLIR image sequences using intensity variation function and template modeling[J].IEEE Transactions on Instrument and Measurment,2005,54(5):1846~1852.
[2]  Yilmaz A,Shafique K,Shah M.Target tracking in airborne forward looking infrared imagery[J].Image Vision Computing Journal,2003,21(7):623~635.
[3]  Comanciu D,Visvanathan R,Meer P.Kernel-based object tracking J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564~575.
[4]  Vapnik Vladimir N.The Nature of Statistical Learning Theory (2nd ed.)[M].Berlin Heidelberg,New York:Springer-Verlag,2000.
[5]  Schapire Robert E,Singer Yoram.Improved boosting algorithms using confidence-rated predictions[J].Machine Learning,1999,37(3):297~336.
[6]  Valentini Giorgio,Dietterich Thomas G.Bias-variance analysis of support vector machines for the development of svm-based ensemble methods[J].Journal of Machine Learning Research,2004,5(7):725~775.
[7]  Braithwaite R N,Bhanu B.Hierarchical gabor filters for object detection in infrared images[A].In:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],Seattle,Washington,USA,1994:628-631.
[8]  Dawoud Amer,Alam M S.Target tracking in infrared imagery using weighted composite reference function-based decision fusion[J].IEEE Transactions on Image Processing,2006,15(2):404~410.
[9]  Yilmaz A,Shafique K,Lobo Niels,et al.Target-tracking in FLIR imagery using mean-shift and global motion compensation[A].In:Proceedings of IEEE Workshop Computer Vision Beyond Visible Spectrum[C],Kauai,HI,USA,2001:445~451.
[10]  Patra J C,Widjaja F,Dss A,et ad.A fast neural network-based detection and tracking of dim moving targets in FLIR imagery[A].In:Proceedings of International Joint Conference on Neural Networks[C],Montreal,Canada,2005:3144~3148.
[11]  Shai Avidan.Ensemble tracking[A].In:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],San Diego,CA,USA,2005,2:494~501.
[12]  Li Xu-chun,Wang Lei,Sung Eric.A study of AdaBoost with SVM based weak learners[A].In:Proceedings of International Joint Conference on Neural Networks[C],Montreal,Canada,2005:196~201.
[13]  Dietterich Thomas G.An experimental comparison of three methods for constructing ensembles of decision trees:Bagging,boosting,and randomization[J].Machine Learning,2000,40(2):139~157.
[14]  Kobi Levi,Yair Weiss.Learning object detection from a small number of examples:the Importance of good features[A].In:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],Washington,DC,USA,2004,2:53~60.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133