UltraGlove: Hand Pose Estimation with Mems-Ultrasonic Sensors

TL;DR

This paper introduces UltraGlove, a low-cost hand-tracking glove using MEMS-ultrasonic sensors and deep learning to accurately estimate hand pose, overcoming limitations of visual and IMU-based methods.

Contribution

The paper presents a novel ultrasonic sensor-based glove and a deep network for robust, accurate hand pose estimation, addressing issues like occlusion and magnetic interference.

Findings

Accurate hand pose reconstruction from ultrasonic distance measurements

Robust performance under external interference

Design and implementation of sensor configuration and model architecture

Abstract

Hand tracking is an important aspect of human-computer interaction and has a wide range of applications in extended reality devices. However, current hand motion capture methods suffer from various limitations. For instance, visual-based hand pose estimation is susceptible to self-occlusion and changes in lighting conditions, while IMU-based tracking gloves experience significant drift and are not resistant to external magnetic field interference. To address these issues, we propose a novel and low-cost hand-tracking glove that utilizes several MEMS-ultrasonic sensors attached to the fingers, to measure the distance matrix among the sensors. Our lightweight deep network then reconstructs the hand pose from the distance matrix. Our experimental results demonstrate that this approach is both accurate, size-agnostic, and robust to external interference. We also show the design logic for the sensor selection, sensor configurations, circuit diagram, as well as model architecture.