一种基于粒子滤波的时空上下文视觉跟踪算法

Visual Tracking Algorithm for Spatio-temporal Context Based on Particle Filter

为解决时空上下文视觉跟踪算法在目标处于遮挡及复杂背景情况下容易产生跟踪漂移的问题,提出了一种基于粒子滤波的时空上下文视觉跟踪算法.通过设置实验参数,自动选择第一帧目标所在的矩形区域,在后续帧跟踪的过程中,利用Bhattacharyya系数作为判断是否遮挡的依据,当目标发生遮挡时,引入粒子滤波对目标在后续帧中位置及运动轨迹进行估计和预测,实现了目标的精确跟踪.实验结果表明,该算法不仅能够适用于光照变化、目标旋转、背景区域干扰等复杂背景下的视觉目标跟踪,并且对目标的遮挡具有鲁棒性,满足实时性要求.

As visual tracking via spatio-temporal context learning easily fails to track target stably when target is in the occlusion condi- tion and complex background,a visual tracking algorithm for spatio-temporal context based on particle filter is proposed. By setting ex- perimental parameters,the rectangle area of the fast frame target is selected automatically. During following frame tracking,the Bhatta- charyya coefficient is used as a judgement criterion for occlusion. When the target is occluded,the particle filter is used to estimate and predict position and trajectory of target in the subsequent frame,and the target can be traced accurately. The experimental results show that the proposed algodthra can not only be applied to visual target tracking under complex conditions such as illumination changes,target rotation and background disturbance,but also has robustness to target occlusion and satisfies the requirements of real-time tracking.