GaitFormer: Two-Stream Transformer Gait Recognition Using Wearable IMU Sensors in the Context of Industry 5.0

The rising attention to human-centricity, a core value of Industry 5.0, makes researchers propose various methods to place humans in the center of production, such as the human digital twin (HDT) and gait identity recognition. However, previous HDT applications in the Industry 5.0 era have less consideration of identity recognition, the vital way to link physical signals to personal archives in cyber systems. Herein GaitFormer, a two-stream transformer gait recognition method is proposed for application with the wearable inertial measurement unit (IMU) motion capture system. GaitFormer consists of temporal and channel modules enclosing Gaussian range encoding (GRE), multihead autocorrelation mechanism, and multiscale as convolutional neural network (CNN) layers. It outperforms state-of-the-art architectures with extensive experiments over publicly available IMU-based datasets, respectively: whuGait and OU-ISIR. Then, the study intends to combine the motion capture system and gait identity recognition algorithm to propose an application of personal monitoring in the human-cyber-physical-system (HCPS), which uses GaitFormer to recognize the identity of the user with motion capture system and show their corresponding customized HDT. This work may contribute to making a connection between gait identity recognition and HDT, constructing personal working profiles in the environment of Industry 5.0.