利用动态步态图进行步态识别

基于轮廓的步态识别方法容易受行人的携带物、衣物等遮挡因素的影响。针对这一问题提出了动态步态图。动态步态图将步态轮廓图划分为动态部分和静态部分，更有利于提取受遮挡影响较小的动态步态信息。设计了双路步态识别网络(Bi-Route)提取步态特征，通过增加动态特征占比，稀释静态特征占比降低遮挡物的影响。网络以动态步态图为输入，使用二维卷积分别提取步态序列中的全局轮廓特征和帧级轮廓特征，使用三维卷积神经网络从帧级轮廓特征中提取动态特征。为了验证本方法的有效性，在CASIA-B数据集上进行了评估，在正常(NM)、背包(BG)、穿大衣(CL)条件下的准确率分别达到了92.9%、87.2%和65.6%。结果表明本方法可以降低遮挡、衣物和携带物等对识别准确率的影响。

Gait recognition based on dynamic gait image

The appearance-based gait recognition methods are easily affected by the carrying objects, clothing and other occlusion factors.In order to solve this problem, Dynamic Gait Image is proposed. Dynamic Gait Image divide gait image into dynamic part and static part,which is more conductive to extract dynamic information less affected by occlusion factors. This paper proposes Bi-Route gait recognitionnetwork, which can minimize the influence of occlusion factors by increasing the proportion of dynamic features and reducing theproportion of static features. The global silhouettes features and frame level silhouettes features of the gait sequences were extracted by2D-convolutional neural network with the input of dynamic gait image. Then 3D-convolutional neural network extracts dynamic featuresfrom frame level silhouettes features. The accuracy of the proposed method evaluated on CASIA-B dataset is 92. 9%, 87. 2% and 65. 6%in NM, BG and CL conditions. The result shows that the proposed method can reduce the impact of occlusion factors.