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

基于Online AdaBoost的偏振图像目标跟踪
引用本文:邢晨,薛模根,袁广林,王峰.基于Online AdaBoost的偏振图像目标跟踪[J].合肥工业大学学报(自然科学版),2011(11):1650-1654.
作者姓名:邢晨  薛模根  袁广林  王峰
作者单位:陆军军官学院5系;陆军军官学院4系;陆军军官学院2系;
基金项目:国家自然科学基金资助项目(40876095)
摘    要:根据偏振图像的特点,文章提出一种基于在线AdaBoost的目标跟踪方法.该方法以最小二乘回归作为弱分类器,以强度、偏振度和边缘方向特征组成的向量为其输入;通过AdaBoost算法将多个弱分类器集成为强分类器,并在跟踪过程中利用AdaBoost算法对强分类器进行在线更新,以适应目标与背景的变化;利用强分类器生成当前置信图...

关 键 词:偏振图像  目标跟踪  在线集成  特征融合

Polarization image object tracking based on Online AdaBoost
XING Chen,XUE Mo-gen,YUAN Guang-lin,WANG feng.Polarization image object tracking based on Online AdaBoost[J].Journal of Hefei University of Technology(Natural Science),2011(11):1650-1654.
Authors:XING Chen  XUE Mo-gen  YUAN Guang-lin  WANG feng
Institution:XING Chen1,XUE Mo-gen2,YUAN Guang-lin3,WANG feng2(1.Fifth Dept.,Academy of Army Officers,Hefei 230031,China,2.Fourth Dept.,3.Second Dept.,China)
Abstract:A polarization image object tracking method is proposed based on Online Adaboost.The least square regression is used as the weak classifier,with feature vectors of intensity,polarization degree and margin direction chosen for the input.The ensemble of weak classifiers is integrated into a strong classifier by AdaBoost algorithm,and this strong classifier is updated online by AdaBoost algorithm during tracking in order to adapt to the change of the object or the background.Current confidence map is given by ...
Keywords:polarization image  target tracking  Online AdaBoost  feature fusion  
本文献已被 CNKI 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