Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging

TL;DR

Ultra Inertial Poser introduces a scalable 3D human pose estimation method that combines inertial sensors with ultra-wideband ranging to significantly improve tracking accuracy and reduce jitter without stationary anchors.

Contribution

The paper presents a novel approach that fuses inertial measurements with inter-sensor distance estimates using a lightweight tracker and graph-based learning, enabling accurate motion capture from sparse sensors.

Findings

Reduced position error by 22% compared to previous methods.

Lowered jitter by 97%, enhancing motion smoothness.

Achieved state-of-the-art performance on a new multi-sensor dataset.

Abstract

While camera-based capture systems remain the gold standard for recording human motion, learning-based tracking systems based on sparse wearable sensors are gaining popularity. Most commonly, they use inertial sensors, whose propensity for drift and jitter have so far limited tracking accuracy. In this paper, we propose Ultra Inertial Poser, a novel 3D full body pose estimation method that constrains drift and jitter in inertial tracking via inter-sensor distances. We estimate these distances across sparse sensor setups using a lightweight embedded tracker that augments inexpensive off-the-shelf 6D inertial measurement units with ultra-wideband radio-based ranging$-$dynamically and without the need for stationary reference anchors. Our method then fuses these inter-sensor distances with the 3D states estimated from each sensor Our graph-based machine learning model processes the 3D states and distances to estimate a person's 3D full body pose and translation. To train our model, we synthesize inertial measurements and distance estimates from the motion capture database AMASS. For evaluation, we contribute a novel motion dataset of 10 participants who performed 25 motion types, captured by 6 wearable IMU+UWB trackers and an optical motion capture system, totaling 200 minutes of synchronized sensor data (UIP-DB). Our extensive experiments show state-of-the-art performance for our method over PIP and TIP, reducing position error from $13.62$ to $10.65cm$ ($22\%$ better) and lowering jitter from $1.56$ to $0.055km/s^3$ (a reduction of $97\%$).