Towards Human Motion Tracking: An Open-source Platform based on Multi-sensory Fusion Methods

Cheng Xu, Ran Su, Yulin Chen, Shihong Duan

Abstract: Human motion tracking (HMT) has been a research focus in the last decades. In this paper, we propose an IMU/TOA-fusion-based platform to solve this problem. Firstly, Time-of-arrival (TOA)-based distance ranging method is considered to compensate for the drifting errors and accumulation introduced by inertial sensors. Secondly, a geometrical kinematic model and maximum correntropy criterion (MCC)-based Kalman filter method are proposed to fuse the multiple information. The open-source hardware and software are detailed in this paper for real-time human motion capture and reconstruction applications. Experiment results show that our proposed hardware can be easily equipped for total body motion reconstruction with a considerable enhancement of the wear-ability and comfort. Furthermore, the main achievements have been presented with a performance comparison between the proposed platform and state-of-the-art commercial ones. Above all, our proposed platform can significantly suppress the accumulative error and drifting problem of conventional inertial systems. More importantly, it realizes the open-source software and hardware, thus it has promising prospects for wearable human motion tracking applications.