[论文] Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body...

论文概要

研究领域: CV
作者: Zhilin Guo, Boqiao Zhang, Oszkár Urbán, Josef Bengtson, Hakan Aktas, Wenzhao Li, Siyu Hong, Kyle Fogarty, Chenliang Zhou, Ali Senguel, Cengiz Oztireli
发布时间: 2026-09-28
arXiv: 2609.35764

中文摘要

稀疏惯性姿态估计有望通过消费级设备实现无摄像头动作捕捉，但消费级传感器不可靠：固件融合的方向有偏，佩戴方式因场景而异，数据流会漂移或中断。在一个新的 35 段单被试基准上（耳机头部 IMU 配对两只智能鞋垫足部 IMU，以 SAM-3D-Body 伪真值标签），我们证明了可靠性问题是通道级的：通道消融实验分离出足部加速度是最具信息量的输入（66.6mm vs. 仅头部 79.0mm），而固件融合的足部方向是破坏收益的负担。因此我们让模型学习对每条流每个通道的信任程度：每流每通道块一个时间门控，使用合成损坏的预训练数据进行辅助可靠性目标训练。通道门控模型在干净数据上是我们所有学习融合方案中最准确的（69.4mm vs. 静态 83.7、无门控 86.6），并且在所有模拟故障下表现最佳；其门控在干净的实际数据上无需测试时监督即可抑制原生有偏的足部方向通道，并以 0.92-0.999 AUROC 标记中断突发。学习对可靠性进行门控而非依赖传感器数量，是实现可部署稀疏惯性捕捉的关键杠杆。

原文摘要

Sparse inertial pose estimation promises camera-free motion capture from consumer devices, but consumer sensors are unreliable: firmware-fused orientations are biased, mounting varies between sessions, and streams drift or drop out. On a new 35-take single-subject benchmark pairing an earbud head inertial measurement unit (IMU) with two smart-insole foot IMUs (SAM-3D-Body pseudo-ground-truth labels), we show the reliability problem is channel-level: a channel ablation isolates foot acceleration as the most informative input (66.6 mm vs. 79.0 mm head-only) and the firmware-fused foot orientation as the liability that destroys the gain. We therefore let the model learn how much to trust each channel of each stream: one temporal gate per stream per channel block, trained with an auxiliary rel...

自动采集于 2026-09-30

#论文 #arXiv #CV #小凯