遮挡情况下基于Kalman均值偏移的目标跟踪

Object Tracking Based on Kalman-Mean Shift in Occlusions

针对经典的Mean-Shift算法在目标发生遮挡时容易导致跟踪失败的问题,提出一种改进的均值偏移跟踪算法。将目标的运动在较短时间内看作一时不变系统,通过引入Kalman滤波进行参数辨识而使发生遮挡后的跟踪系统具有后续状态预测的能力。整个跟踪过程分为Mean-Shift跟踪下的Kalman参数辨识和基于Kalman状态估计的Bhattacharyya系数分析两个子过程交替执行。对不同的视频序列测试的结果表明,算法能够对发生遮挡后的目标进行持续、稳健的跟踪。

An improved Mean-Shift-based tracking algorithm was proposed to solve the poor tracking ability problem in occlusions. A time-invariant system was used to describe the movement of the target during a short time sequences, and through Kalman filter this system was identified so as to make it have ability estimate the coming states while occlusions taken place. The whole tracking system could 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. Experiment results of variant video sequences demonstrate that the proposed method can track the objects stably and accurately during occlusions.