A Deep Learning Approach for Non-Contact Heart Rate Monitoring

neonatal_video_heart_rate

Deep learning pipeline for video-based heart rate prediction in neonates, leveraging signals from multiple body regions.

Content

1. RhythmNet Model

2. Dataset

── 2.1 stmaps dataloader

── 2.2 data augmentations

── 2.3 st_maps generation

3. Model Training

Usage

• Install dependencies

conda env create -f environment.yml

References

[1] X. Niu, S. Shan, H. Han, and X. Chen, RhythmNet: End-to-end heart rate estimation from face via spatial-temporal representation,'' IEEE Trans. Imag. Proces., vol. 29, pp. 2409-2423, 2020, doi: 10.1109/TIP.2019.2947204.

The model and loss function scripts are adapted from the RhythmNet code repository:

https://github.com/AnweshCR7/RhythmNet