Procjena broja otkucaja srca iz videa

master's thesis

• Title (english): Estimating Heart Rate from Video
• Author: Tomislav Kurtović
• Mentor: Tomislav Pribanić (mentor)
• Committee member: Tomislav Pribanić (predsjednik povjerenstva)
• Committee member: Marko Subašić (član povjerenstva)
• Committee member: Tomislav Petković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Metoda Eulerove videomagnifikacije poznata je u zadnjih deset godina kao postupak
vizualiziranja promjena boje kože uslijed dotoka krvi. Ključ ove metode nalazi se u konstrukciji Gaussovih piramida i računanju Fourierove transformacije. Ovaj rad proširuje metodu EVM tako što uz vizualizaciju promjena boje kože procjenjuje numeričku vrijednost broja otkucaja srca u videozapisu. U radu se opisuje postupak implementacije EVM metode kao i korištenu metodu za procjenu pulsa. Nakon implementacije sustava slijedi analiza koja prikazuje usporedbu procjene broja otkucaja sa stvarnim vrijednostima. Subjekti istraživanja su u mirovanju ili pokretu i za analizu se uzimaju različiti dijelovi lica i tijela da bi se u zaključku dale daljnje smjernice i opažanja.

Abstract (english)

The Euler videomagnification method has been known for the past ten years as a procedure for
visualizing skin color changes due to blood flow. The key to this method lies in the construction of Gaussian pyramids and the calculation of the Fourier transform. This paper extends the EVM method by estimating the numerical value of the heart rate in the video in addition to visualizing skin color changes. The paper describes the implementation procedure of the EVM method as well as the method used for heart rate estimation. The implementation of the system is followed by an analysis that shows a comparison of the estimate of the number of beats with the actual values. The research subjects are at rest or in motion and different parts of the face and body are taken for analysis in order to give further guidelines and observations in the conclusion.

• Keywords: racunalni vid; Fourierova transformacija; procesuiranje signala; python
• Keywords (english): computer vision; Fourier transform; signal processing; python
• Language: croatian
• URN:NBN: urn:nbn:hr:168:533150
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-07-13 10:15:42