Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errors
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916242705612800 |
|---|---|
| author | Moryossef, Amit |
| author_facet | Moryossef, Amit |
| contents | This paper addresses a critical flaw in MediaPipe Holistic's hand Region of Interest (ROI) prediction, which struggles with non-ideal hand orientations, affecting sign language recognition accuracy. We propose a data-driven approach to enhance ROI estimation, leveraging an enriched feature set including additional hand keypoints and the z-dimension. Our results demonstrate better estimates, with higher Intersection-over-Union compared to the current method. Our code and optimizations are available at https://github.com/sign-language-processing/mediapipe-hand-crop-fix. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_03545 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errors Moryossef, Amit Computer Vision and Pattern Recognition This paper addresses a critical flaw in MediaPipe Holistic's hand Region of Interest (ROI) prediction, which struggles with non-ideal hand orientations, affecting sign language recognition accuracy. We propose a data-driven approach to enhance ROI estimation, leveraging an enriched feature set including additional hand keypoints and the z-dimension. Our results demonstrate better estimates, with higher Intersection-over-Union compared to the current method. Our code and optimizations are available at https://github.com/sign-language-processing/mediapipe-hand-crop-fix. |
| title | Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.03545 |