用手机摄像头小数据训练，实时估算髋外骨骼用户关节运动
Personalization of Wearable Sensor-Based Joint Kinematic Estimation Using Computer Vision for Hip Exoskeleton Applications
- 用迁移学习将视觉模型适配到新用户，仅需1-2个步态周期数据
- 相比仅用正常或僵直步态训练的模型，误差降低9.7%至19.9%
- 适合临床人群的可穿戴机器人应用，无需专业设备
准确的下肢关节运动估计对患者监测、康复和外骨骼控制至关重要。以往基于可穿戴传感器的深度学习模型需大量新数据才能适应新步态模式。计算机视觉领域的人体姿态估计模型虽易部署且支持实时推理，但在无法使用摄像头的场景中不可行。为此，我们提出一种基于计算机视觉的深度学习适配框架，实现实时关节运动估计。该框架仅需少量数据（1-2个步态周期），无需专业动作捕捉系统。通过迁移学习，我们将时间卷积网络（TCN）适配至僵硬膝步态数据，使模型在根均方误差上分别比仅在正常人和僵硬膝数据上训练的TCN降低9.7%和19.9%。本框架展示了智能手机摄像头训练的深度学习模型在临床人群中的实时关节运动估计潜力，适用于可穿戴机器人。
原文摘要 · Abstract (English)
Accurate lower-limb joint kinematic estimation is critical for applications such as patient monitoring, rehabilitation, and exoskeleton control. While previous studies have employed wearable sensor-based deep learning (DL) models for estimating joint kinematics, these methods often require extensive new datasets to adapt to unseen gait patterns. Meanwhile, researchers in computer vision have advanced human pose estimation models, which are easy to deploy and capable of real-time inference. However, such models are infeasible in scenarios where cameras cannot be used. To address these limitations, we propose a computer vision-based DL adaptation framework for real-time joint kinematic estimation. This framework requires only a small dataset (i.e., 1-2 gait cycles) and does not depend on professional motion capture setups. Using transfer learning, we adapted our temporal convolutional network (TCN) to stiff knee gait data, allowing the model to further reduce root mean square error by 9.7% and 19.9% compared to a TCN trained on only able-bodied and stiff knee datasets, respectively. Our framework demonstrates a potential for smartphone camera-trained DL models to estimate real-time joint kinematics across novel users in clinical populations with applications in wearable robots.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。