A new tracking scheme that is based on feature fusion is proposed.In this paper,by combining the gray space and gradient space,our target model is represented in the form of a weighting histogram using its gray feature and gradient feature,and frame-to-frame tracking is performed using mean shift.Experiments turned out the algorithm works efficiently and robustly for the occluding object tracking and the tracking when the gray scale of target and background are similar.
参考文献
相似文献
引证文献
引用本文
刘素珍,邓和林.一种基于特征融合的运动目标跟踪算法[J].激光与红外,2008,38(8):837~840 LIU Su-zhen, DENG He-lin. A Moving Object Tracking Algorithm Based on Feature Fusion[J]. LASER & INFRARED,2008,38(8):837~840