Unobtrusive Monitoring of Sensorimotor Performance in Ground-Based Functional Tasks

Astronauts returning from extended microgravity exposure frequently exhibit alterations in sensorimotor function leading to postural imbalance and impaired locomotion. Mission duration and individual responses often influence both the severity of performance decrements and the variability in adaptation timelines. Postflight disruptions during functional tasks are often detected through body-worn inertial measurement unit (IMU) devices. While IMU sensors are relatively compact, long-term wear may lead to discomfort, displacement on the body, and restrictions in movement or crew behavior. While IMU data offers valuable research insights, interpreting changes in preflight and postflight measures can be impractical for crew support personnel, limiting its use in medical assessments and rehabilitation. Finally, the availability of inertial sensors in-flight is limited. There is a need for unobtrusive monitoring tools to improve our ability to monitor adaptation following gravitational transitions in various postflight evaluations and rehabilitation settings. Markerless motion capture (MMC) is an evolving unobtrusive technology providing 3D human pose estimation from multiple synchronized 2D camera views using deep learning algorithms. The markerless technology can revolutionize how data is captured on Earth and potentially in-flight during intravehicular activity by leveraging onboard camera hardware. The following paper presents an evaluation of a state-of-the-art commercial-off-the-shelf MMC system, Theia3D, compared to traditional IMU devices during various functional tasks and environmental conditions. Concurrent data are analyzed for nine participants of varying anthropometry. The analysis includes limited assessments of clothing (i.e., a flight suit), camera availability, and testing settings. The average root mean square deviations were less than five degrees for all functional tasks evaluated in both a laboratory and field-testing location. The field-testing location led to slightly higher deviations in head and trunk estimation. Functional tasks with more dynamic requirements resulted in larger deviations. The limited assessment of clothing indicates that a flight suit has a minimal impact on the estimation accuracy of the head and torso, and the impact can be further minimized via partial donning. The development of visualization tools to enhance the application of the pose estimation output is also presented. These tools offer effective methods for anonymizing sensitive crew data, facilitating numerous applications across research, medical, and rehabilitation groups. This work lays the foundation for future use of MMC to track recovery to baseline performance and inform rehabilitation protocols to enhance crew readiness for daily activities.