Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2312.06892 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913238286860288 |
|---|---|
| author | Rouast, Philipp V. |
| author_facet | Rouast, Philipp V. |
| contents | This report introduces VitalLens, an app that estimates vital signs such as heart rate and respiration rate from selfie video in real time. VitalLens uses a computer vision model trained on a diverse dataset of video and physiological sensor data. We benchmark performance on several diverse datasets, including VV-Medium, which consists of 289 unique participants. VitalLens outperforms several existing methods including POS and MTTS-CAN on all datasets while maintaining a fast inference speed. On VV-Medium, VitalLens achieves mean absolute errors of 0.71 bpm for heart rate estimation, and 0.76 bpm for respiratory rate estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_06892 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | VitalLens: Take A Vital Selfie Rouast, Philipp V. Computer Vision and Pattern Recognition Human-Computer Interaction This report introduces VitalLens, an app that estimates vital signs such as heart rate and respiration rate from selfie video in real time. VitalLens uses a computer vision model trained on a diverse dataset of video and physiological sensor data. We benchmark performance on several diverse datasets, including VV-Medium, which consists of 289 unique participants. VitalLens outperforms several existing methods including POS and MTTS-CAN on all datasets while maintaining a fast inference speed. On VV-Medium, VitalLens achieves mean absolute errors of 0.71 bpm for heart rate estimation, and 0.76 bpm for respiratory rate estimation. |
| title | VitalLens: Take A Vital Selfie |
| topic | Computer Vision and Pattern Recognition Human-Computer Interaction |
| url | https://arxiv.org/abs/2312.06892 |