基于CamShift的目标跟踪算法

Object tracking algorithm based on CamShift

CamShift是一种应用颜色信息的跟踪算法,在跟踪过程中,CamShift利用目标的颜色直方图模型得到每帧图像的颜色投影图,并根据上一帧跟踪的结果自适应调整搜索窗口的位置和大小,从而得到当前图像中目标的尺寸和中心位置。在CamShift算法基础上对搜索窗口进行简单运动预测,并增加二次搜索方法,提高跟踪的稳定性。实验结果表明,在图像背景复杂且目标不规则运动的情形下,仍能有效地跟踪到目标。

CamShift is a color-based tracking algorithm. In the process of object tracking, CamShift operates on a back-projection image produced from object histogram model. Computed information is used previously to adjust current search window size and location, then the location and size of the color object are found. Simple motion prediction and twice searching methods to improve tracking performance are devised. Finally the experimental results indicate that color object is efficiently tracked even with complex background and irregular motion by using this algorithm.