基于粒子滤波改进的行人跟踪算法

Pedestrian Tracking Algorithm based on Modified Particle Filtering

为了提高汽车安全辅助驾驶技术和减少道路交通事故,根据行人运动变化特点,对基于粒子滤波的跟踪算法进行改进,提出一种新的行人跟踪算法。通过将空间距离中心加权和相关信息相结合的颜色直方图的观测模型方法,实现行人目标跟踪。实验结果表明,与基于HSV空间颜色直方图的粒子滤波跟踪算法相比,该算法有效解决复杂背景下局部遮挡和全遮挡问题,并在鲁棒性方面明显地优于前一种算法。

A new pedestrian tracking algorithms based on modified particle filtering is proposed to reduce road traffic accidents and based on variable characteristics of pedestrian movements, to improve the supplementary driving technologies for vehicle safety. With color histogram for observation model and combined with weight based on spatial center- distance and correlation information, the pedestrian tracking is achieved. The experimental results show that, compared with particle filter tracking algorithm based on color histogram in HSV space, this algorithm could more effectively solve local blocking and global blocking problems in complex background, and has fairly better robustness.