Open-Source Virtual IMU Sensor Platform for Developing a Customized Wearable Human Activity Recognition System

Building a wearable human activity recognition (HAR) system follows complicated steps, making the wearable HAR system development time-consuming, cumbersome, and error-prone. One of the critical challenges is its dataset collection, which typically requires a group of people to perform specified motions for an extensive period to capture data. Recently, cross-modal virtual inertial measurement unit (IMU) data generation from 3-D avatars has been recognized as a key solution to address the costly and laborious sensor dataset collection for HAR system establishment. However, the utilization of virtual IMU data still faces the challenge of tedious steps, including expensive computing resources, model training, and domain transfer, among others. This article presents a novel platform employing the input of 3-D avatar motion sequences. Combined with the virtual IMU data generation mechanism, the motion modification-based virtual IMU data augmentation approach is designed to generate the virtual IMU training dataset. The platform supports various sensor placement selections, data processing, model training, fine-tuning, and deployment functionalities. The proposed platform integrates the whole process of developing a wearable HAR system. Due to the fewer requirements in the real world, it could enable the wearable HAR system building to become low-cost, customized, and contribute to HAR system prototyping and related application scenarios.