摘要
CamShift算法是一种利用颜色信息对移动目标进行跟踪的算法,当目标快速运动或者受到干扰时容易导致跟踪失败。因此提出了一种结合CamShift与扩展卡尔曼滤波的移动目标跟踪算法,使用扩展卡尔曼滤波对目标运动速度和空间位置进行预测,同时采用目标加权直方图改进CamShift算法。所研究的算法能有效地克服目标背景干扰,存在干扰目标或目标部分被遮挡的情况下,仍能实现有效跟踪。实验结果表明,所研究的方法能够对移动目标持续稳定地跟踪。
In CamShift algorithm,color information is used for tracking the moving target,which may lead to failed tracking if the speed of the target is too high or disturbance exists.Therefore,we proposed an algorithm combining Extended Kalman Filter（EFK） with CamShift algorithm for tracking moving target,in which EKF can predict the position and the velocity of the moving target.On the other hand,the weighted histogram is used to improve CamShift algorithm.The proposed tracking algorithm can effectively overcome the influence of the background,which could still achieve effective tracking when disturbance exists or the target is partially sheltered.Experimental results show that the proposed method can obtain the stable tracking performance for the moving target.
出处
《电光与控制》
北大核心
2011年第4期1-5,共5页
Electronics Optics & Control
基金
光电控制技术重点实验室资助
