Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.09034 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911800220450816 |
|---|---|
| author | Zhu, Dali Zhang, Wenli Zeng, Hualin Liu, Xiaohao Yang, Long Zheng, Jiaqi |
| author_facet | Zhu, Dali Zhang, Wenli Zeng, Hualin Liu, Xiaohao Yang, Long Zheng, Jiaqi |
| contents | Remote photoplethysmography (rPPG) technique extracts blood volume pulse (BVP) signals from subtle pixel changes in video frames. This study introduces rFaceNet, an advanced rPPG method that enhances the extraction of facial BVP signals with a focus on facial contours. rFaceNet integrates identity-specific facial contour information and eliminates redundant data. It efficiently extracts facial contours from temporally normalized frame inputs through a Temporal Compressor Unit (TCU) and steers the model focus to relevant facial regions by using the Cross-Task Feature Combiner (CTFC). Through elaborate training, the quality and interpretability of facial physiological signals extracted by rFaceNet are greatly improved compared to previous methods. Moreover, our novel approach demonstrates superior performance than SOTA methods in various heart rate estimation benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_09034 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | rFaceNet: An End-to-End Network for Enhanced Physiological Signal Extraction through Identity-Specific Facial Contours Zhu, Dali Zhang, Wenli Zeng, Hualin Liu, Xiaohao Yang, Long Zheng, Jiaqi Computer Vision and Pattern Recognition Remote photoplethysmography (rPPG) technique extracts blood volume pulse (BVP) signals from subtle pixel changes in video frames. This study introduces rFaceNet, an advanced rPPG method that enhances the extraction of facial BVP signals with a focus on facial contours. rFaceNet integrates identity-specific facial contour information and eliminates redundant data. It efficiently extracts facial contours from temporally normalized frame inputs through a Temporal Compressor Unit (TCU) and steers the model focus to relevant facial regions by using the Cross-Task Feature Combiner (CTFC). Through elaborate training, the quality and interpretability of facial physiological signals extracted by rFaceNet are greatly improved compared to previous methods. Moreover, our novel approach demonstrates superior performance than SOTA methods in various heart rate estimation benchmarks. |
| title | rFaceNet: An End-to-End Network for Enhanced Physiological Signal Extraction through Identity-Specific Facial Contours |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.09034 |