Package pyVHR (short for Python framework for Virtual Heart Rate) is a comprehensive framework for studying methods of pulse rate estimation relying on video, also known as remote photoplethysmography (rPPG).
The methodological rationale behind the framework is that in order to study, develop and compare new rPPG methods in a principled and reproducible way, the following conditions should be met: i) a structured pipeline to monitor rPPG algorithms' input, output, and main control parameters; ii) the availability and the use of multiple datasets; iii) a sound statistical assessment of methods' performance. pyVHR allows to easily handle rPPGmethods and data, while simplifying the statistical assessment. Its main features lie in the following:
- Analysis-oriented. It constitutes a platform for experiment design, involving an arbitrary number of methods applied to multiple video datasets. It provides a systemic end-to-end pipeline, allowing to assess different rPPG algorithms, by easily setting parameters and meta-parameters.
- Openness. It comprises both method and dataset factory, so to easily extend the pool of elements to be evaluatedwith newly developed rPPG methods and any kind of videodatasets.
- Robust assessment. The outcomes are arranged intostructured data ready for in-depth analyses. Performance comparison is carried out based on robust nonparametric statistical tests.
Nine classical rPPG methods, namely ICA, PCA, GREEN, CHROM, POS, SSR, LGI, PBV, OMIT, as well as the recent Deep Learning-based model MTTS-CAN are implemented. Moreover, pyVHR provides APIs for handling 11 publicly available video datasets, i.e. PURE, LGI-PPGI-DB, UBFC-1, , UBFC-2, UBFC-Phys, ECG-Fitness, MAHNOB Vicar-PPG-2, V4V , VIPL-HR and COHFACE, usually adopted to benchmark rPPG methods. Eventually, extensive rigorous statistical analyses can be effortlessly performed via the pyVHR stats APIs.
The quickest way to get started is to install the miniconda distribution, a lightweight minimal installation of Anaconda Python.
Once installed, create a new conda environment and automatically fetch all the dependencies based on your architecture (with or without GPU), using one of the following commands:
CPU-only version
conda env create --file https://raw.githubusercontent.com/phuselab/pyVHR/pyVHR_CPU/pyVHR_CPU_env.ymlCPU+GPU version
This yml environment is for cudatoolkit=11.3 and python=3.9.
conda env create --file https://raw.githubusercontent.com/phuselab/pyVHR/master/pyVHR_env.ymlEnter the newly created conda environment and install the latest stable release build of pyVHR with:
CPU-only version
conda activate pyvhr
(pyvhr) pip install pyvhr-cpuCPU+GPU version
conda activate pyvhr
(pyvhr) pip install pyvhrRun the following code to obtain BPM estimates over time for a single video:
from pyVHR.analysis.pipeline import Pipeline
import matplotlib.pyplot as plt
pipe = Pipeline()
time, BPM, uncertainty = pipe.run_on_video('/path/to/video', roi_approach="patches", roi_method="faceparsing")
plt.figure()
plt.plot(time, BPM)
plt.fill_between(time, BPM-uncertainty, BPM+uncertainty, alpha=0.2)
plt.show()The full documentation of run_on_video method, with all the possible parameters, can be found here: https://phuselab.github.io/pyVHR/
The notebooks folder contains useful Jupyter notebooks.
The full documentation of the pyVHR framework is available at https://phuselab.github.io/pyVHR/.
In the folder realtime you can find an example of a simple GUI created using the pyVHR package.
You can launch it by going into the path pyVHR/realtime/ and using the command
python GUI.pyIf you want to use a specific rPPG method and pre-post filterings, you must set them in the last lines of GUI.py.
Below is a video showing the use of the GUI.
GUI.mp4
The latest unstable development build of pyVHR is available on GitHub, and can be obtained downloading from source and installing via:
git clone git@github.com:phuselab/pyVHR.git
cd pyVHR/
python setup.py installThe main branch refers to the full pyVHR framework (requires GPU), while the pyVHR_CPU branch is dedicated to the CPU-only architectures.
If you want to create your environment from scratch you should follow these steps:
- Install PyTorch (here)
- Install Numba (here)
- Install Cupy (for GPU only) with the correct CUDA version (here)
- Install CuSignal (for GPU only) using conda and remove from the command 'cudatoolkit=x.y' (here)
- Install Kaleido (here)
- Install PyTables (here)
- Install pyVHR as shown above.
The framework contains the implementation of many common methods for remote-PPG measurement. Currently implemented methods with reference publications are:
Green / Verkruysse, W., Svaasand, L. O., & Nelson, J. S. (2008). Remote plethysmographic imaging using ambient light. Optics express, 16(26), 21434-21445.
CHROM / De Haan, G., & Jeanne, V. (2013). Robust pulse rate from chrominance-based rPPG. IEEE Transactions on Biomedical Engineering, 60(10), 2878-2886.
ICA / Poh, M. Z., McDuff, D. J., & Picard, R. W. (2010). Non-contact, automated cardiac pulse measurements using video imaging and blind source separation. Optics express, 18(10), 10762-10774.
LGI / Pilz, C. S., Zaunseder, S., Krajewski, J., & Blazek, V. (2018). Local group invariance for heart rate estimation from face videos in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 1254-1262).
PBV / De Haan, G., & Van Leest, A. (2014). Improved motion robustness of remote-PPG by using the blood volume pulse signature. Physiological measurement, 35(9), 1913.
PCA / Lewandowska, M., Rumiński, J., Kocejko, T., & Nowak, J. (2011, September). Measuring pulse rate with a webcam—a non-contact method for evaluating cardiac activity. In 2011 federated conference on computer science and information systems (FedCSIS) (pp. 405-410). IEEE.
POS / Wang, W., den Brinker, A. C., Stuijk, S., & de Haan, G. (2016). Algorithmic principles of remote PPG. IEEE Transactions on Biomedical Engineering, 64(7), 1479-1491.
SSR / Wang, W., Stuijk, S., & De Haan, G. (2015). A novel algorithm for remote photoplethysmography: Spatial subspace rotation. IEEE transactions on biomedical engineering, 63(9), 1974-1984.
OMIT / Álvarez Casado, C., Bordallo López, M. (2022). Face2PPG: An unsupervised pipeline for blood volume pulse extraction from faces. arXiv (eprint 2202.04101).
MTTS-CAN / Liu, X., Fromm, J., Patel, S., & McDuff, D. (2020). Multi-task temporal shift attention networks for on-device contactless vitals measurement. Advances in Neural Information Processing Systems, 33, 19400-19411.
Interfaces for 10 different datasets are provided in the datasets folder. Once the datasets are obtained, the respective files must be edited to match the correct path.
Currently supported datasets are:
COHFACE / https://www.idiap.ch/dataset/cohface
LGI-PPGI / https://github.com/partofthestars/LGI-PPGI-DB
MAHNOB-HCI / https://mahnob-db.eu/hci-tagging/
PURE / https://www.tu-ilmenau.de/neurob/data-sets-code/pulse-rate-detection-dataset-pure
UBFC1 / https://sites.google.com/view/ybenezeth/ubfcrppg
UBFC2 / https://sites.google.com/view/ybenezeth/ubfcrppg
UBFC-Phys / https://sites.google.com/view/ybenezeth/ubfc-phys
ECG-Fitness / https://cmp.felk.cvut.cz/~spetlrad/ecg-fitness/
Vicar-PPG-2 / https://docs.google.com/forms/d/e/1FAIpQLScwnW_D5M4JVovPzpxA0Bf1ZCTaG5vh7sYu48I0MVSpgltvdw/viewform
V4V / https://vision4vitals.github.io/
VIPL-HR https://arxiv.org/abs/1810.04927
If you use this code, please cite the paper:
@article{Boccignone2020,
doi = {10.1109/access.2020.3040936},
url = {https://doi.org/10.1109/access.2020.3040936},
year = {2020},
publisher = {Institute of Electrical and Electronics Engineers ({IEEE})},
pages = {1--1},
author = {Giuseppe Boccignone and Donatello Conte and Vittorio Cuculo and Alessandro D’Amelio and Giuliano Grossi and Raffaella Lanzarotti},
title = {An Open Framework for Remote-{PPG} Methods and their Assessment},
journal = {{IEEE} Access}
}
This project is licensed under the GPL-3.0 License - see the LICENSE file for details