View in EDS

Towards Extended Interaction with Differential Magnetic Tracking and Deep Learning.

Saved in:
Bibliographic Details
Title: Towards Extended Interaction with Differential Magnetic Tracking and Deep Learning.
Authors: Chen, Zhenyu (AUTHOR), Chen, Peihang (AUTHOR), Huang, Jingyuan (AUTHOR), Chen, Dongyao (AUTHOR)
Source: International Journal of Human-Computer Interaction. Jun2026, Vol. 42 Issue 11, p8402-8425. 24p.
Subjects: Magnetic sensors, Deep learning, Mixed reality, Automatic tracking, Computer input design, Data augmentation
Abstract: Recent advancements in extended reality (XR) technologies have heightened the demand for robust and intuitive input methods. Conventional optical tracking in VR/AR suffers from occlusion, thus severely undermining practicality. Magnetic sensing has emerged as a promising alternative due to its inherent resistance to occlusion, no drift, and low power consumption. However, popular tracking approaches, e.g., LM-based, are highly sensitive to initial parameter settings, while deep learning-based methods remain unsuitable for mobile scenarios. To address these limitations, we propose MagDelta, a novel extended input system combining differential magnetic field measurements with a deep learning framework. To reduce the overhead of data collection, we employed a combination of data synthesis and data interpolation strategies. Experiments show MagDelta achieves a 3D positioning error of 5.60 mm at 10 cm and a trajectory error of 2.06 mm. MagDelta demonstrates robustness to various real-world factors such as device orientation and environmental conditions. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Human-Computer Interaction is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Psychology and Behavioral Sciences Collection
Description
Abstract:Recent advancements in extended reality (XR) technologies have heightened the demand for robust and intuitive input methods. Conventional optical tracking in VR/AR suffers from occlusion, thus severely undermining practicality. Magnetic sensing has emerged as a promising alternative due to its inherent resistance to occlusion, no drift, and low power consumption. However, popular tracking approaches, e.g., LM-based, are highly sensitive to initial parameter settings, while deep learning-based methods remain unsuitable for mobile scenarios. To address these limitations, we propose MagDelta, a novel extended input system combining differential magnetic field measurements with a deep learning framework. To reduce the overhead of data collection, we employed a combination of data synthesis and data interpolation strategies. Experiments show MagDelta achieves a 3D positioning error of 5.60 mm at 10 cm and a trajectory error of 2.06 mm. MagDelta demonstrates robustness to various real-world factors such as device orientation and environmental conditions. [ABSTRACT FROM AUTHOR]
ISSN:10447318
DOI:10.1080/10447318.2025.2565394