传感器通道中的运动模式的步态识别算法

Gait recognition algorithm based on motion pattern in sensor passage

提出一种基于运动模式的步态识别算法,应用于轨道交通自动售检票系统的由闸机构成的传感器通道中,对行走者和物体进行识别。算法是在检测人体步态的XYT模型的基础上进行改进,用红外传感器替代摄像头采集个体的通行信息,将连续状态的XYT模型改进成离散状态的步态识别算法,通过定义一些符合人体步态特征的特殊的复合模式,即步态模式来区分人与物体。实验证明,该算法用于闸机的智能识别系统是有效的。

A gait recognition algorithm based on motion pattern was presented, which was applied to identify passengers and objects in sensor passage consisted of gates in automatic fare system in railway traffic. The algorithm was improved on the XYT model which was used to detect the human gait. The infrared sensor instead of camera was used to collect the individual access information, and the XYT model in a continuous state was changed into the gait recognition algorithm in a discrete state. By defining the composite model consistent with the special characteristics of human gait as the gait model, the passenger and the object could be distinguished. Experimental results show that the gait recognition algorithm is effective.