Detecting Pulse from Head Motions in Video

By Guha Balakrishnan, Frédo Durand, John V. Guttag. 2013

585 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Cardiology and Cardiovascular Medicine

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Cardiology and Cardiovascular Medicine

Citations in the corpus

Learning-based Video Motion Magnification (2018, background): “The ability to discern small motions enables important applications such as understanding a building’s structural health [3] and measuring a person’s vital sign [4].”
Remote Heart Rate Measurement from Face Videos under Realistic Situations (2014, methodology): “All these mentioned methods [2, 10, 12, 13] have the following limitations while considering the adaptability and robustness in general application scenarios:”
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals (2019, methodology): “Ob-serving subtle color and motion based signals from videos [58, 15] enabled methodologies like remote photoplethys-mography (rPPG or iPPG) [47, 43] and head motion based ballistocardiogram (BCD) [7] for non-intrusive heart rate detection from facial RGB videos.”
Ballistocardiography and Seismocardiography: A Review of Recent Advances (2015, methodology): “with the head-to-foot (longitudinal) direction ballistocardiographic displacements of the head being captured and processed from video recordings [33].”
RhythmNet: End-to-End Heart Rate Estimation From Face via Spatial-Temporal Representation (2019, methodology): “Besides rPPG-based HR measurement, another kind of remote HR estimation methods is based on the ballistocardiographic (BCG) signals, which is the subtle head motions caused by cardiovascular circulation.”
Computer Vision and Image Understanding (2016, background): “In order to keep only the most stable reference points and discard erratic trajectories, the maximum distance traveled by each point between consecutive frames is calculated and points with a distance exceeding the mode of the distribution are discarded ( Balakrishnan et al., 2013 ).”
Remote measurement of cognitive stress via heart rate variability (2014, methodology): “[14] presented a method for recovering the BVP waveform from motion of the human head allowing the heart rate to be detected even if no skin is visible.”
A Survey of Methods for Safe Human-Robot Interaction (2017, methodology): “This could be accomplished through software, such as an algorithm that derives heart rate from video data (Balakrishnan et al., 2013), or hardware, such as a less-intrusive method of electroencephalography (EEG) sensors (Emotiv, 2014).”
Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks (2019, methodology): “In earlier studies of rPPG, most methods [1, 4, 10, 13, 14, 21, 22, 23] can be seen as a two-stage pipeline, which first detects or tracks the face to extract the rPPG signals, and then estimates the corresponding average HR from frequency analysis.”
Self-Adaptive Matrix Completion for Heart Rate Estimation from Face Videos under Realistic Conditions (2016, methodology): “These subtle changes encompass both color [27] and motion [4] and they are induced by the internal functioning of the heart.”
DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks (2018, methodology): “Computer analysis of videos and images can be used to recover these signals [30, 24, 3] and magnify them [40, 14].”
Non-contact video-based vital sign monitoring using ambient light and auto-regressive models (2014, background): “Interestingly, the latest paper from a third MIT group (Balakrishnan et al 2013) hypothesizes that there are also motion-induced changes in the cardiac -synchronous changes in the reﬂected ambient light.”
Smart Homes that Monitor Breathing and Heart Rate (2015, background): “rate [8, 44]; however, such video-based techniques require the user to face the camera and do not work when he/she turns around or is outside the camera’s field of view.”
Video magnification in presence of large motions (2015, methodology): “While usually too small to notice, such variations can be magniﬁed computationally to reveal a fascinating and meaningful world of small motions [7, 2, 17, 11, 14, 15].”