Database Open Access
Video Pulse Signals in Stationary and Motion Conditions
Published: July 12, 2017. Version: 1.0.0
A. Melchor Rodríguez and J. Ramos Castro, Pulse rate variability analysis by video using face detection and tracking algorithms, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, 2015, pp. 5696-5699. doi: 10.1109/EMBC.2015.7319685Please include the standard citation for PhysioNet:
Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals (2003). Circulation. 101(23):e215-e220.
The data set contains 40 pulse signal recordings obtained from 15 healthy volunteers (12 men and 3 women between 23 and 35 years). For each subject, there is a simultaneous face video recording, and a finger pulse recording reference system, in a sitting position. The video pulse signals were obtained from videos recorded by two camera models at 15 and 60 frames per second, which were then further processed. The reference finger pulse sensor had a sampling frequency of 1 kHz. There is a time offset between the reference and video signals, commented in the WFDB header files.
As part of the study, only 5 subjects were recorded by both cameras. Two recordings of about 1 min were acquired for each subject in stationary and motion conditions. 50s of the recordings were performed in order to analyze the same record length in all subjects.
The record name is formed as subj_x_y_z_s where:
- x: number of subject
- y: condition of the recording (s = stationary; m = motion)
- z: camera (c1 = camera 1 (Logitech model); c2 = camera 2 (GoPro model))
- s: the signal (vid = video pulse; ref = reference finger pulse)
A. Melchor Rodríguez (angel.melchor at upc.edu) and J. Ramos-Castro (juan.jose.ramos at upc.edu)
Anyone can access the files, as long as they conform to the terms of the specified license.
License (for files):
Open Data Commons Attribution License v1.0
Files on Google Cloud
Click here to view the files in the Google Cloud Console. Login with a Google account is required.
Total uncompressed size: 5.5 MB.Download Zip (5.5 MB)