【摘要】 针对图像序列目标匹配跟踪中出现模板漂移导致目标丢失的问题,提出一种基于距离加权平均绝对差的模板漂移抑制算法。对传统的最小绝对差准则进行改进,利用模板边缘到中心的距离作为参数对实时图与基准图的绝对差结果进行加权,增大失配位置漂移误差,使得真实位置的绝对差最小以防止模板更新过程中产生漂移。研究结果表明:该算法可以在跟踪中有效抑制模板漂移,实现对形变目标的长时间稳定跟踪,实时性好,便于在实时系统中实现。更多还原

【Abstract】 For the problem of robust filter design based on networked control system,using a Lyapunov-Krasovskii function and an integral inequality approach,the criteria for robust H ∞ performance analysis of filtering-error systems were proposed by retaining some useful terms which are used to discard the derivative of Lyapunov-Krasovskii function and deal with the different parts of uncertainties of the systems separately.An improved design method of robust H ∞ filter was proposed in term of linear matrix inequalities.Numerical examples results show that the proposed method is less conservative.更多还原