Personalization of Wearable Sensor-Based Joint Kinematic Estimation Using Computer Vision for Hip Exoskeleton Applications
This addresses the need for personalized, real-time joint kinematic estimation in clinical populations using wearable robots, though it is incremental as it builds on existing methods.
The paper tackled the problem of adapting joint kinematic estimation for hip exoskeletons to unseen gait patterns by proposing a computer vision-based deep learning framework that reduces root mean square error by 9.7% and 19.9% compared to baseline models using only a small dataset.
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.