摘要
为解决复杂背景下运动目标的跟踪,提出一种新的基于Mean-shift的目标跟踪算法,该方法首先通过运动检测方法分割出跟踪目标区域,然后通过卡尔曼滤波算法预测下一帧跟踪窗口的起点,在此基础上采用Mean-Shift算法跟踪目标区域;实验结果表明在有干扰的条件下算法仍能实时有效地进行跟踪,与传统方法相比具有更好的自适应性、稳定性、鲁棒性以及更高的识别率。
To solve the problem of infrared target tracking based on complex baekground, a new target tracking algorithm based on Mean--shift is proposed. The method firstly segments object tracking region through motion detection method, and predicts starting point of next frame tracking window through Kalman filtering algorithm, then use Mean--shift algorithm to track object on the basis. The result proves in the interference conditions the algorithm can track the target effectively, with better adaptability, stability, robustness, and higher recognition.
出处
《计算机测量与控制》
北大核心
2013年第2期502-504,508,共4页
Computer Measurement &Control
基金
国家自然基金(61172185)
天津市高等学校科技发展基金项目(20100705)
