A vision-based pose estimator can serve as the label source to fine-tune an IMU-based temporal convolutional network for a new gait pattern, improving knee and hip angle estimation errors by 10 to 20 percent over non-personalized baselines.
It pays to have a spring in your step,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Personalization of Wearable Sensor-Based Joint Kinematic Estimation Using Computer Vision for Hip Exoskeleton Applications
A vision-based pose estimator can serve as the label source to fine-tune an IMU-based temporal convolutional network for a new gait pattern, improving knee and hip angle estimation errors by 10 to 20 percent over non-personalized baselines.