From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Mengxi, Ray, Lala Shakti Swarup, Bian, Sizhen, Watanabe, Ko, Bhatt, Ankur, Sorysz, Joanna, Torah, Russel, Zhou, Bo, Lukowicz, Paul
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915748683710464
author Liu, Mengxi
Ray, Lala Shakti Swarup
Bian, Sizhen
Watanabe, Ko
Bhatt, Ankur
Sorysz, Joanna
Torah, Russel
Zhou, Bo
Lukowicz, Paul
author_facet Liu, Mengxi
Ray, Lala Shakti Swarup
Bian, Sizhen
Watanabe, Ko
Bhatt, Ankur
Sorysz, Joanna
Torah, Russel
Zhou, Bo
Lukowicz, Paul
contents We present NeckSense, a novel wearable system for head pose tracking that leverages multi-channel bio-impedance sensing with soft, dry electrodes embedded in a lightweight, necklace-style form factor. NeckSense captures dynamic changes in tissue impedance around the neck, which are modulated by head rotations and subtle muscle activations. To robustly estimate head pose, we propose a deep learning framework that integrates anatomical priors, including joint constraints and natural head rotation ranges, into the loss function design. We validate NeckSense on 7 participants using the current SOTA pose estimation model as ground truth. Our system achieves a mean per-vertex error of 25.9 mm across various head movements with a leave-one-person-out cross-validation method, demonstrating that a compact, line-of-sight-free bio-impedance wearable can deliver head-tracking performance comparable to SOTA vision-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12884
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation
Liu, Mengxi
Ray, Lala Shakti Swarup
Bian, Sizhen
Watanabe, Ko
Bhatt, Ankur
Sorysz, Joanna
Torah, Russel
Zhou, Bo
Lukowicz, Paul
Computer Vision and Pattern Recognition
Signal Processing
We present NeckSense, a novel wearable system for head pose tracking that leverages multi-channel bio-impedance sensing with soft, dry electrodes embedded in a lightweight, necklace-style form factor. NeckSense captures dynamic changes in tissue impedance around the neck, which are modulated by head rotations and subtle muscle activations. To robustly estimate head pose, we propose a deep learning framework that integrates anatomical priors, including joint constraints and natural head rotation ranges, into the loss function design. We validate NeckSense on 7 participants using the current SOTA pose estimation model as ground truth. Our system achieves a mean per-vertex error of 25.9 mm across various head movements with a leave-one-person-out cross-validation method, demonstrating that a compact, line-of-sight-free bio-impedance wearable can deliver head-tracking performance comparable to SOTA vision-based methods.
title From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation
topic Computer Vision and Pattern Recognition
Signal Processing
url https://arxiv.org/abs/2507.12884