改进的核相关滤波目标跟踪算法

Improved Object Tracking Algorithm Based on Kernelized Correlation Filter

提出一种基于核相关滤波的尺度和旋转自适应跟踪算法.首先,利用核相关滤波确定目标的中心位置;然后,使用特征点匹配的方式估计目标的尺度变化和旋转角度.在特征点匹配过程中,使用前、后两次光流匹配消除不稳定特征点;计算特征点对的权重分布,从而估计出目标的最佳尺度和角度;判断当前目标是否受到遮挡,进而使用更合理的方式更新特征点集和目标模型,进一步提高算法的鲁棒性.实验结果表明:文中算法不仅能在一定程度上处理目标外观变化问题,而且跟踪的实时性较好.

A scale and rotation adaptive tracking algorithm based on kernelized correlation filter is proposed. Firstly, the algorithm determines the center positon of the object via kernelized correlation filter. Then the al-gorithm estimates the scale changes and rotation angle of an object using keypoints matching. In the process of keypoints matching, the method eliminates unstable keypoints using forward and backward matching. The next, the algorithm estimates the optimal scale and angle by considering the weight of keypoints. At last, the method detects whether the target is occluded, and then update keypoints set and object model more reasona-ble, and hence improving the robustness of the algorithm. The results of experiments show that the proposed algorithm not only can handle changes of object’s appearance to a certain degree,but also have high tracking efficiency.