Filament Sliding Linear Potentiometer-Based Data Glove (FLiPo) for Precisely Annotating Human Finger Poses
Zhisheng Xia, Haochen Yong, Qilong Liu, Zhenghao Ke, Han Ding, Zhigang Wu
AI summary
Problem
Existing data gloves either heavily occlude the hand, hindering visual annotation, or lack precise joint angle regression, while vision-only methods struggle with occlusion and ground-truth data scarcity.
Approach
The device uses 0.1 mm filaments attached to finger skin to transmit joint arc length changes to linear potentiometers on the forearm, mapping these lengths to joint angles via a fully connected neural network.
Key results
- 2.15° mean absolute error in joint angle estimation
- High environmental stability with only 7.54‰ signal variation under extreme conditions
- Negligible visual occlusion due to ultra-thin filaments and arm-mounted sensors
- Robust long-term repeatability with minimal drift after 12,600 cycles
Why it matters
Provides a reliable, low-occlusion ground-truth annotation tool for training vision-based hand tracking models in robotics and HCI.
Abstract
Data gloves offer excellent portability and a strong ability to handle occluded movements, making them more advan- tageous over other methods for capturing complex hand motions in unstructured environments. However, the majority of existing hand-motion-capture gloves do not preserve visual features of the hand, which critically hinders their applicability for automatic pose annotation in RGB images. Here, we propose a data glove based on filament-sliding linear potentiometers (FLiPo), which can maintain finger appearance and ensure high accuracy as well as robustness, paving the way for automatic annotation. In FLiPo, fine filaments (Φ 0.1 mm) are deployed on finger skin to transmit joint arc length variations as well as preserve the hand’s visual fea- tures, while linear potentiometers used to capture filament length changes are positioned on the arm. Simultaneously, a quantitative occlusion scoring metric is proposed to evaluate the degree of finger occlusion caused by the device. Further, we experimentally analyze the nonlinearities induced by biaxial joint coupling and skin tissue artifact (STA)-related hysteresis, and employ a fully connected neural network to map arc length to joint angles with an MAE of joint angles of 2.15°. Meanwhile, tests under challenging environmental conditions, including heat, moisture, and magnetic interference, are conducted to evaluate its stability. Finally, the system’s capability for real-time pose capture with high accuracy, robustness, and low occlusion was demonstrated.