基于认知分析的手势跟踪方法研究

摘要

Aiming at reducing particle numbers, starting from analyzing operators' cognitive model, a novel particle filtering hand gesture tracking approach is put forward. At Erst, operators' cognitive psychology during hand gesture operation processes is analyzed and a human hand motion dynamic model is established. Next, some fundamental characteristics of the dynamic model are studied and a description method is presented. Then, a status variable microstructure based hand gesture tracking algorithm is presented. Results show that, using only a small number of particles, comparatively accurate results can be obtained.%以降低粒子数目为目标,以分析操作者的认知模型为切入点,提出一种新的粒子滤波手势跟踪方法.首先,分析操作者在手势操作过程中的认知心理,建立人手运动的动态模型.其次,研究动态模型的基本特征,并给出一种描述方法.然后,提出一种基于状态变量微观结构的手势跟踪算法.结果表明,采用所介绍的算法,用少量粒子就可以得到比较精确的跟踪结果.