|
Enhancing Stroke Rehabilitation at Home: Evaluating MediaPipe for Human Pose Estimation |
|---|---|
| รหัสดีโอไอ | |
| Creator | Norapat Labchurat |
| Title | Enhancing Stroke Rehabilitation at Home: Evaluating MediaPipe for Human Pose Estimation |
| Contributor | Worawat Choensawat, Kingkarn Sookhanaphibarn |
| Publisher | The Association of Council of IT Deans (CITT) |
| Publication Year | 2566 |
| Journal Title | Journal of Information Science and Technology |
| Journal Vol. | 13 |
| Journal No. | 1 |
| Page no. | 45-53 |
| Keyword | Computer vision, MediaPipe, Human pose estimation, Rehabilitation, Fugl-Meyer Assessment, Home-based rehabilitation, Upper limb rehabilitation |
| URL Website | https://tci-thaijo.org/index.php/JIST |
| Website title | Journal of Information Science and Technology |
| ISSN | 2651-1053 |
| Abstract | This research experiment evaluates the accuracy of MediaPipe, a computer vision technology, in estimating human pose compared to motion capture technology. The experiment utilizes posesderived from the Fugl-Meyer Assessment for upper extremity (FMA-UE). Webcams are installed at three positions: front 90บ, left 40บ, and right 140บ of the participant, while participants wear motion capture suits.The experiment begins with simultaneous movements performed on both sides of the body, with data recorded from both systems simultaneously. We calculateangles of body jointsand comparethe accuracy percentage. The results indicate that MediaPipe's accuracy in estimating pose based on the FMA-UE was not significantly high. Due to limitations in estimating poses in the vertical planefrom z-axisand the range resulted in wider angles than reality. However,the usage of normalization for 2D angle calculation presentsthe better accuracy. Therefore, MediaPipe can still be used for developing interactive applicationsand assist the doctor evaluate patient, but further research and development are needed for evaluating patients during FMA-UE exercises. |
