Abstract: In order to overcome the target recognition difficulties caused by the noise，occlusion and the changing of the background，a lot of tracking algorithms have been proposed.This paper presents an integrating target tracking algorithm based on HSV color space.A time-invariant system is used to describe the movement of the target during a short time sequences，and through Kalman filter this system is identified so as to make it have ability to predict the coming states while occlusions take place.The whole tracking system can be divided into two parts：A Kalman parameter identifying system based on the object tracking and a Bhattacharyya coefficient analyzing system based on the Kalman state estimating；in the tracking process those two parts run by turns according to different cases.The experiment has confirmed validity and accuracy of this algorithm.

Key words: color space shift, target tracking, mean-shift, Kalman filter, fusion algorithm

摘要： 为了克服噪声、遮挡、背景的改变等对目标识别带来的困难，出现了很多的跟踪算法。提出了一种基于HSV色彩空间的目标跟踪融合算法，即在较短时间内，将目标的运动看作一时不变系统，引入卡尔曼滤波进行参数辨识，使得跟踪系统具有后续状态预测的能力。算法包括均值漂移算法跟踪下利用卡尔曼滤波对后续状态预测和基于卡尔曼滤波状态估计的Bhattacharyya系数分析两个子过程，整个跟踪过程分两个子过程交替执行。对不同的视频序列测试的结果表明，算法能够对目标进行持续、稳健的跟踪。验证了新方法的有效性和准确性。

关键词: 色彩空间转换, 目标跟踪, 均值漂移, 卡尔曼滤波, 算法融合