形态学动态人体追踪方法

摘要

It presents a novel method of tracking moving body in clutter background. It uses the moving difference to find the region of interest,then makes a mask of a target through the modality algorithm using the skeleton of the object,and revises the mask combined Kalman predictive tracking method to achieve the real time tracking. It is proved that in clutter background and noisy situation this algorithm is still efficient.%提出了一种基于形态学的动态人体追踪方法,通过运动差分的方法找出感兴趣区域,通过形态学的方法消去背景和噪声,进行边缘提取.边缘提取后采用骨架化特征描述目标,建立特征点模板,并通过模板评价函数进行不断的模版修正,结合Kalman预测追踪方法来达到实时动态目标的追踪,实验证明,该方法具有一定的鲁棒性.