摘要
针对传统的Mean Shift跟踪算法不能适应目标尺度变化、遮挡的情况,以及易于陷入局部极值的问题,本文提出了一种增强型Mean Shift跟踪算法。该算法采用变化的核函数带宽进行跟踪,在目标未被遮挡的情况下更新目标模型,并且引入Kalman滤波器预测目标位置,有效的解决了上述问题。实验结果表明,本文提出的增强型Mean Shift跟踪算法具有较高的准确性和实时性。
In order to solve the problems of scale change, occlusion and falling into local extremum in traditional Mean Shift tracking, this paper proposes an enhanced Mean Shift tracking algorithm. It utilizes changing bandwidths of kernel function for tracking, updates the target model when not being occluded, introduces Kalman filter to predict target position, and then effectively solves the problems above. Experimental results show that the proposed algorithm has good accuracy and high real time quality.
