基于运动估计的Kalman滤波视频对象跟踪

Kalman filtering for tracking video objects based on motion estimation

提出了一种利用Kalman滤波对运动目标的形心进行预测,从而实现视频对象跟踪的算法。首先进行视频对象分割,求出运动目标的形心。再利用视频序列中连续两帧的形心和运动矢量信息,用Kalman滤波对运动目标的形心在下一帧的位置进行预测,从而快速、有效地自动跟踪多个目标对象。实验结果表明,该算法对运动目标的出现和消失,以及非刚性物体的尺度变化和变形,具有较强的鲁棒性。

A video tracking algorithm that used the prediction of object centroids based on Kalman filtering was preposed. Firstly, video objects were segmented and their centroids were calculated. Then, Kalman filtering was used to predict the object centroids in next frame with the information of centroids and motion vectors in successive two frames of a video sequence, so It was able to track multiple non-rigid moving objects fast, efficiently and automatically. Experimental results show that the proposed method is robust to deal with the problems in multi-targets tracking such as new target entering, target leaving, scaling and deforming of non-rigid objects.