基于分段仿射的双侧学习目标跟踪  

Target Tracking of Bilateral Learning Based on Piecewise Affine

作　　者：刘崇文[1] 胡淑芳[2] 任成娟[1] 陈波[1] 

机构地区：[1]重庆大学计算机学院,重庆400030 [2]重庆理工大学设备处,重庆400054

出　　处：《重庆理工大学学报（自然科学）》2011年第10期54-60,共7页Journal of Chongqing University of Technology：Natural Science

基　　金：国家"863"计划重点资助项目(2007AA01Z423)

摘　　要：结合分段仿射目标跟踪方法中仿射变换参数的思想,对双侧学习的目标跟踪方法进行了改变,以达到对运动目标跟踪的良好效果。通过重新定义双侧学习方法中的均值和协方差等重要参数,使这些参数适合运动目标跟踪,并设计出相应的方法。实验结果表明,该方法比基于颜色的双侧学习方法效果更好。This paper combined the idea of affine exchange parameters in piecewise affine targets tracking method,and improved the bilateral learning targets tracking method to achieve the goal of the exercise of good results in targets tracking.The paper redefined some important parameters in bilateral learning such as mean and covariance,and made these parameters fit target tracking,and designed the corresponding method.Experiments show that the method in this paper has better effect than bilateral learning color-based tracking.

关 键 词：目标跟踪 分段仿射 双侧学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]