Supervised learning approach to remote heart rate estimation from facial videos

Supervised learning approach to remote heart rate estimation from facial videos. Osman, A., Turcot, J., & El Kaliouby, R. In 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), pages 1–6, Ljubljana, May, 2015. IEEE.

Paper doi abstract bibtex

A supervised machine learning approach to remote video-based heart rate (HR) estimation is proposed. We demonstrate the possibility of training a discriminative statistical model to estimate the Blood Volume Pulse signal (BVP) from the human face using ambient light and any offthe-shelf webcam. The proposed algorithm is 120 times faster than state of the art approach and returns a conﬁdence metric to evaluate the HR estimates plausibility. The algorithm was evaluated against the state-of-the-art on 120 minutes of face videos, the largest video-based heart rate evaluation to date. The evaluation results showed a 53% decrease in the Root Mean Squared Error (RMSE) compared to state-of-the-art.

@inproceedings{osman_supervised_2015,
	address = {Ljubljana},
	title = {Supervised learning approach to remote heart rate estimation from facial videos},
	isbn = {978-1-4799-6026-2},
	url = {http://ieeexplore.ieee.org/document/7163150/},
	doi = {10.1109/FG.2015.7163150},
	abstract = {A supervised machine learning approach to remote video-based heart rate (HR) estimation is proposed. We demonstrate the possibility of training a discriminative statistical model to estimate the Blood Volume Pulse signal (BVP) from the human face using ambient light and any offthe-shelf webcam. The proposed algorithm is 120 times faster than state of the art approach and returns a conﬁdence metric to evaluate the HR estimates plausibility. The algorithm was evaluated against the state-of-the-art on 120 minutes of face videos, the largest video-based heart rate evaluation to date. The evaluation results showed a 53\% decrease in the Root Mean Squared Error (RMSE) compared to state-of-the-art.},
	language = {en},
	urldate = {2020-07-17},
	booktitle = {2015 11th {IEEE} {International} {Conference} and {Workshops} on {Automatic} {Face} and {Gesture} {Recognition} ({FG})},
	publisher = {IEEE},
	author = {Osman, Ahmed and Turcot, Jay and El Kaliouby, Rana},
	month = may,
	year = {2015},
	pages = {1--6},
}

Downloads: 0

{"_id":"YwDKbR6fkD5sboRaC","bibbaseid":"osman-turcot-elkaliouby-supervisedlearningapproachtoremoteheartrateestimationfromfacialvideos-2015","author_short":["Osman, A.","Turcot, J.","El Kaliouby, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Ljubljana","title":"Supervised learning approach to remote heart rate estimation from facial videos","isbn":"978-1-4799-6026-2","url":"http://ieeexplore.ieee.org/document/7163150/","doi":"10.1109/FG.2015.7163150","abstract":"A supervised machine learning approach to remote video-based heart rate (HR) estimation is proposed. We demonstrate the possibility of training a discriminative statistical model to estimate the Blood Volume Pulse signal (BVP) from the human face using ambient light and any offthe-shelf webcam. The proposed algorithm is 120 times faster than state of the art approach and returns a conﬁdence metric to evaluate the HR estimates plausibility. The algorithm was evaluated against the state-of-the-art on 120 minutes of face videos, the largest video-based heart rate evaluation to date. The evaluation results showed a 53% decrease in the Root Mean Squared Error (RMSE) compared to state-of-the-art.","language":"en","urldate":"2020-07-17","booktitle":"2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)","publisher":"IEEE","author":[{"propositions":[],"lastnames":["Osman"],"firstnames":["Ahmed"],"suffixes":[]},{"propositions":[],"lastnames":["Turcot"],"firstnames":["Jay"],"suffixes":[]},{"propositions":[],"lastnames":["El","Kaliouby"],"firstnames":["Rana"],"suffixes":[]}],"month":"May","year":"2015","pages":"1–6","bibtex":"@inproceedings{osman_supervised_2015,\n\taddress = {Ljubljana},\n\ttitle = {Supervised learning approach to remote heart rate estimation from facial videos},\n\tisbn = {978-1-4799-6026-2},\n\turl = {http://ieeexplore.ieee.org/document/7163150/},\n\tdoi = {10.1109/FG.2015.7163150},\n\tabstract = {A supervised machine learning approach to remote video-based heart rate (HR) estimation is proposed. We demonstrate the possibility of training a discriminative statistical model to estimate the Blood Volume Pulse signal (BVP) from the human face using ambient light and any offthe-shelf webcam. The proposed algorithm is 120 times faster than state of the art approach and returns a conﬁdence metric to evaluate the HR estimates plausibility. The algorithm was evaluated against the state-of-the-art on 120 minutes of face videos, the largest video-based heart rate evaluation to date. The evaluation results showed a 53\\% decrease in the Root Mean Squared Error (RMSE) compared to state-of-the-art.},\n\tlanguage = {en},\n\turldate = {2020-07-17},\n\tbooktitle = {2015 11th {IEEE} {International} {Conference} and {Workshops} on {Automatic} {Face} and {Gesture} {Recognition} ({FG})},\n\tpublisher = {IEEE},\n\tauthor = {Osman, Ahmed and Turcot, Jay and El Kaliouby, Rana},\n\tmonth = may,\n\tyear = {2015},\n\tpages = {1--6},\n}\n\n","author_short":["Osman, A.","Turcot, J.","El Kaliouby, R."],"key":"osman_supervised_2015","id":"osman_supervised_2015","bibbaseid":"osman-turcot-elkaliouby-supervisedlearningapproachtoremoteheartrateestimationfromfacialvideos-2015","role":"author","urls":{"Paper":"http://ieeexplore.ieee.org/document/7163150/"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/shamimown","dataSources":["Wo3KRwzN9T9tb8ucf"],"keywords":[],"search_terms":["supervised","learning","approach","remote","heart","rate","estimation","facial","videos","osman","turcot","el kaliouby"],"title":"Supervised learning approach to remote heart rate estimation from facial videos","year":2015}