窗口尺寸变化目标的遮挡跟踪  

MeanShift Tracking Algorithm with the Adaptive Bandwidth of the Target in Occlusions

作　　者：林庆[1,2] 陈远祥[1] 王士同[2,3] 詹永照[1] 

机构地区：[1]江苏大学计算机科学与通信工程学院,镇江212013 [2]南京理工大学计算机系,南京210094 [3]江南大学信息学院,无锡214122

出　　处：《计算机科学》2010年第8期273-275,289,共4页Computer Science

基　　金：国家自然科学基金项目(60673190)资助

摘　　要：针对传统的MeanShift跟踪算法在目标发生遮挡时容易导致目标丢失的情况,提出了一种改进的MeanShift跟踪算法。将多尺度空间理论、Kalman滤波器与遮挡算法相结合,当目标发生遮挡后,利用Kalman估计目标信息量,能对目标尺寸有后续跟踪能力。实验结果表明,当目标发生遮挡后,改进的跟踪算法对目标无论增大或减小都能连续地、自动地选择大小合适的跟踪窗口。An improved Mean-Shift-based tracking algorithm was proposed to solve the poor tracking ability problem in occlusions. Combinating multi-scale space theory, Kalman filter and occlusion, it can have a good tracking about scale u- sing Kalman when target has been occluded. The experimental results show that the improved algorithm can select the proper size of the tracking window in the scenarios when the target has been occluded.

关 键 词：KALMAN 信息量 MEANSHIFT 遮挡 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]