Mjerenje pulsa iz video snimaka pomoću kalmanovog filtra

master's thesis

• Title (english): Kalman filter-based heartrate measurement from video sequences
• Author: Hrvoje-Tomislav Presečan
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Sven Lončarić (član povjerenstva)
• Committee member: Tomislav Pribanić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-09-23, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu objasnili smo ukratko Kalman filtra. Dali smo kratki pregled statističkih metoda koje se koriste za realizaciju Kalman filtra. Pokazali smo kako je Kalman filtar optimalan rekurzivan algoritam za obradu podataka. Objasnili smo tri modela sustava koji se mogu koristit za implementaciju različitih modela Kalman filtara s primjenom na detekciju RGB boje. Također smo pokazali nedostatke pojedinih modela sustava kao i njihove prednosti, te smo dali usporedbu sva tri modela u kontekstu praćenja promjene RGB boje.

Abstract (english)

In this paper, we have briefly explained the Kalman filter. We gave a brief overview of the statistical methods used for the implementation of Kalman filter. We have shown how the Kalman filter is an optimal recursive algorithm for data processing. We explained three system models that can be used to implement various models of Kalman filter with application to estimation of RGB color in video. We have also demonstrated the shortcomings of individual system model as well as their strengths, and we have made comparison of all three models in the context of tracking changes in values of RGB color.

• Keywords: Kalman filtar; EKF; model sustava; očitavanje periodičnosti; autokorelacija; rekurzivni algoritam; optimalni algoritam
• Keywords (english): Kalman filter; EKF; model of system; error variance; determing period of; autocorrelation; recursiv algorithm; optimal algorithm
• Language: croatian
• URN:NBN: urn:nbn:hr:168:675362
• 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: 2018-02-06 11:25:54