Bob’s implementation of different rPPG algorithms

This module contains the implementation of different remote photoplesthymography (rPPG) algorithms:

• Li’s CVPR14 [li-cvpr-2014].
• CHROM [dehaan-tbe-2013].
• 2SR [wang-tbe-2015].

Also, we provide scripts to infer the heart-rate from the pulse signals, and to evaluate global performance on two different databases: Manhob HCI-Tagging (http://mahnob-db.eu/hci-tagging/) and COHFACE (http://www.idiap.ch/dataset/cohface).

Warning

You should download the databases before trying to run anything below!

Documentation

• Computing bounding boxes
• Li’s CVPR14 user’s guide
  • Step 1: Extract signals from video sequences
  • Step 2: Illumination Rectification
  • Step 3: Non rigid Motion Elimination
  • Step 4: Filtering
• Li’s CVPR14 Python API
  • Signals extraction
  • Illumination rectification
  • Motion correction
  • Filtering
• CHROM user’s guide
  • Extract the pulse signal from video sequence
• CHROM Python API
• 2SR user’s guide
  • Extract the pulse signal from video sequence
• 2SR Python API
• Retrieve the heart-rate and compute performances
  • Frequency analysis and Heart-rate computation
  • Generating performance measures

References

[li-cvpr-2014]

Li X, Chen J, Zhao G & Pietikäinen M. Remote heart rate measurement from face videos under realistic situations IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. pdf

[dehaan-tbe-2013]

de Haan, G. & Jeanne, V. Robust Pulse Rate from Chrominance based rPPG IEEE Transactions on Biomedical Engineering, 2013. pdf

[wang-tbe-2015]

Wang, W., Stuijk, S. and de Haan, G. A Novel Algorithm for Remote Photoplesthymograpy: Spatial Subspace Rotation IEEE Trans. On Biomedical Engineering, 2015

Licensing

This work is licensed under the GPLv3.

Indices and tables

• Index
• Module Index