%0 Journal Article
%T Point matching estimation for moving object tracking based on Kalman filter<br>基于Kalman点匹配估计的运动目标跟踪
%A ZENG Wei
%A ZHU Gui-bin
%A LI Yao
%A <br>曾伟
%A 朱桂斌
%A 李瑶
%J 计算机应用
%D 2009
%I 
%X The classic corner tracking algorithm does not meet the real-time requirement, and may lose the object mostly due to occlusions or/and some similar objects to the object. To solve the problems, a new algorithm based on Kalman Filter (KF) point matching estimation was proposed. Combined with predicting the target's location based on KF and dividing the image into blocks, the extracted multi-scale corner points which are geometrically invariant were given different weights for the responsible function, and the location was tracked by its average vector. The experimental results show that the proposed method can perform well in on-line and robust tracking systems.
%K 运动目标跟踪
%K 目标检测
%K 卡尔曼滤波
%K Harris角点
%K 点匹配估计
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=DA0C6C7C3BA5778BC49C02DE828D97B8&yid=DE12191FBD62783C&vid=771469D9D58C34FF&iid=B31275AF3241DB2D&sid=E8D8D9C05584612B&eid=BFDA25D5ECAB4246&journal_id=1001-9081&journal_name=计算机应用&referenced_num=2&reference_num=18