Abstract
Due to the recent technological advances in inertial measurement units (IMUs), many applications for the measurement of human motion using multiple body-worn IMUs have been developed. In these applications, each IMU has to be attached to a predefined body segment. A technique to identify the body segment on which each IMU is mounted allows users to attach inertial sensors to arbitrary body segments, which avoids having to remeasure due to incorrect attachment of the sensors. We address this IMU-to-segment assignment problem and propose a novel end-to-end learning model that incorporates a global feature generation module and an attention-based mechanism. The former extracts the feature representing the motion of all attached IMUs, and the latter enables the model to learn the dependency relationships between the IMUs. The proposed model thus identifies the IMU placement based on the features from global motion and relevant IMUs. We quantitatively evaluated the proposed method using synthetic and real public datasets with three sensor configurations, including a full-body configuration mounting 15 sensors. The results demonstrated that our approach significantly outperformed the conventional and baseline methods for all datasets and sensor configurations.
Highlights
Inertial measurement units (IMUs) are a prominent option for analyzing human motion
The intra-misassignment denotes that the IMU attached to a part of the limb is misclassified to another part of the same limb
We have presented an approach that identifies the segment on which each IMU is mounted by merging the features of all the body-worn IMUs and by learning the dependency relationships between the sensors
Summary
Inertial measurement units (IMUs) are a prominent option for analyzing human motion. IMUs measure 3D acceleration, angular velocity, and magnetic field, and they calculate their 3D orientation. Body-worn IMUs can be used to estimate rotational and, sometimes, translational motion of the attached segment, which help estimate the required motion parameters. As the sensors operate at a high frame rate with low latency, they can be introduced in real-time applications for motion analysis, such as full-body motion capture [1]–[3] and navigation [4], [5]. Recent technological advances have dramatically reduced the size and price of IMUs, making them the most promising technology for the continuous tracking of human movements in daily life [6]–[8]. Due to recent improvements that have enabled easier configuration, non-expert (but trained)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
