arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2608.15621cs.AIcs.LG

独立位置方向偏移下的旋转不变多IMU活动识别

Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts

Seungyeol Baek, Yoonbyung Chai, Yonghyeon Lee, Sungjoon Choi, Sungho Suh

首次发表
浏览论文内容

中文总结 AI 辅助

针对多IMU部署时各位置独立方向偏移的问题,提出TRI-HAR框架,通过结构设计实现旋转不变性,在多IMU基准测试中优于旋转增强基线。

中文摘要 AI 辅助

使用自行佩戴的可穿戴设备进行人体活动识别(HAR),如居家康复和运动监测,常需在不同会话间重新连接惯性测量单元(IMU)。在多IMU场景中,这会导致身体各位置出现独立的方向偏移,这种部署偏移是传统标量HAR模型无法从结构上处理的。现有解决方法依赖旋转增强,其鲁棒性取决于采样的变换;或依赖校准和方向归一化流程,需要额外的参考框架假设或显式操作。本文提出Truly Rotation-Invariant HAR(TRI-HAR),这是一种旋转不变框架,可使对独立位置IMU方向偏移的鲁棒性成为模型的结构属性。TRI-HAR将加速度计和陀螺仪数据流重塑为三轴向量,对每个IMU位置应用共享的SO(3)等变骨干网络和不变投影,并融合得到的不变特征以进行活动分类。在四个多IMU基准测试中,TRI-HAR在固定独立位置SO(3)旋转下保持了宏F1值,且在该目标偏移下优于旋转增强基线,无需使用旋转增强。

英文摘要

Human Activity Recognition (HAR) with self-administered wearables, such as at-home rehabilitation and exercise monitoring, often requires reattaching inertial measurement units (IMUs) across sessions. In multi-IMU settings, this can induce independent orientation offsets across body locations, a deployment shift that conventional scalar HAR models do not structurally handle. Existing remedies rely on rotation augmentation, whose robustness depends on sampled transformations, or calibration and orientationnormalization pipelines requiring additional reference-frame assumptions or explicit procedures. We present Truly Rotation-Invariant HAR (TRI-HAR), a rotation-invariant framework that makes robustness to independent per-location IMU orientation offsets a structural model property. TRI-HAR reshapes accelerometer and gyroscope streams into triaxial vectors, applies a shared SO(3)-equivariant backbone and invariant projection to each IMU location, and fuses the resulting invariant features for activity classification. Across four multi-IMU benchmarks, TRI-HAR preserves macro-F1 under fixed independent per-location SO(3) rotations and outperforms rotation-augmented baselines under this target shift without requiring rotational augmentation.

发表机构

  • Korea University(高丽大学)
  • Massachusetts Institute of Technology(麻省理工学院)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑