基于二值掩码图像的粒子滤波目标跟踪快速算法

Fast particle filter algorithm for object tracking based on binary mask image

粒子滤波算法是进行运动目标跟踪的一种重要方法。针对传统粒子滤波算法在进行目标跟踪时存在的计算量大、实时性不足的问题,提出一种基于二值掩码图像的粒子滤波目标跟踪快速算法。该算法在传统粒子滤波算法的每个帧处理阶段产生二值掩码图像,再结合权重选择方法移除背景中权重较小的粒子,保留权重较大的重要粒子。提出的算法可以有效减少参与计算的粒子数目,节约算法的计算成本,从而提高目标跟踪的实时性。与传统粒子滤波算法进行比较,实验结果表明,提出的算法不仅能够有效地提高跟踪速度,而且跟踪结果的准确性和鲁棒性也有所增强。

Particle filter algorithm is an important method in the field of moving object tracking. A fast particle filter algorithm for object tracking based on binary mask image is proposed to solve the large calculation and poor real-time problems in traditional particle filter tracking algorithm. In the proposed algorithm, a binary mask image is generated in each frame processing stage of traditional particle filter, then combined with a weight selection method, the particles with lower weight in the background of the mask are removed and the important particles with larger weight are retained. The proposed algorithm can effectively save the calculation cost by reducing the number of particles involved in calculation, and improve the real-time performance of object tracking. The experimental results compared with the traditional particle filter algorithm show that the proposed algorithm can not only improve the tracking speed effectively, but also improve the tracking accuracy and robustness.