Heart Beat Rate Estimation from Video

نویسندگان

  • Pavel Černý
  • Jan Kybic
چکیده

The thesis describes an implementation of a method estimating the heart beat rate based on an analysis of the color changes measured in a video of a human face. We use a 3D facial landmark tracker that allows to extract a stable region on a face needed to acquire a robust measurement of the color changes. A simple model is proposed to approximate a linear projection of the color signal by sinusoid superimposed on a line. The unknown parameters of the model are estimated by the least squares method which has a closed form solution for fixed heart beat rate. The proposed method is implemented partially in C++ and Matlab and it runs real time on a common PC. Another contribution of the thesis is a database of 43 videos containing 8 human subjects annotated with their heart beat rate measured by a precise contact method. The proposed method evaluated on the benchmark provides estimate of the heart rate with average deviation 5.25 BPM from the ground truth annotation. Abstrakt Práce popisuje implementaci metody, odhadujı́cı́ tepovou frekvenci srdce ve videu s lidským obličejem, na principu analyzovánı́ barevných změn. Použı́váme 3D tracker významných bodů tváře k vyjmutı́ stabilnı́ oblasti z obličeje, což je nezbytné pro zı́skánı́ robusnı́ho měřenı́ barevných změn. Je navržen jednoduchý model pro aproximaci lineárnı́ projekce barevného signálu pomocı́ sinusoidy posazené na přı́mku. Neznámé parametry modelu jsou určeny pomocı́ metody nejmenšı́ch čtverců, ta má pro fixnı́ tepovou frekvenci analytické řešenı́. Navrhovaná metoda je implemetovaná částečně v C++ a v Matlabu a běžı́ na běžném PC v reálném čase. Dalšı́m přı́nosem práce je databáze 43 videı́, obsahujı́cı́ch 8 osob, anotovaných jejich tepovou frekvencı́, změřenou pomocı́ přesné kontaktnı́ metody. Navrhovaná metoda, spuštěna na benchmark testu, odhaduje tep s průměrnou odchylkou od anotace 5.25 tepů za minutu.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Multi - Modal Heart - Beat Estimation On an iPhone by Narges Norouzi

Multi-Modal Heart-Beat Estimation On an iPhone Narges Norouzi Master of Applied Science Graduate Department of Electrical and Computer Engineering University of Toronto 2014 Current generation smartphone video cameras and microphones enable photoplethysmography (PPG) and phonocardiography (PCG) acquisition. In this thesis, I utilized the iPhone microphone and camera to measure heart rate. We de...

متن کامل

Blood Pressure and Heart Rate Variabilities Estimation Using Ballistocardiography

In this work a blood pressure and heart rate variability estimation system is presented. Instead of merely using beat-to-beat time interval extracted from the electrocardiogram (ECG), it is also used finger photoplethysmography (PPG) and ballistocardiography (BCG) information to have three independent estimates of the heart rate variability. Since pulse arrival and transit times can be extracte...

متن کامل

Robust inter-beat interval estimation in cardiac vibration signals.

Reliable and accurate estimation of instantaneous frequencies of physiological rhythms, such as heart rate, is critical for many healthcare applications. Robust estimation is especially challenging when novel unobtrusive sensors are used for continuous health monitoring in uncontrolled environments, because these sensors can create significant amounts of potentially unreliable data. We propose ...

متن کامل

A novel technique for fetal heart rate estimation from Doppler ultrasound signal

BACKGROUND The currently used fetal monitoring instrumentation that is based on Doppler ultrasound technique provides the fetal heart rate (FHR) signal with limited accuracy. It is particularly noticeable as significant decrease of clinically important feature - the variability of FHR signal. The aim of our work was to develop a novel efficient technique for processing of the ultrasound signal,...

متن کامل

Unsupervised Heart Rate Variability Estimation from Ballistocardiograms

We propose and evaluate an unsupervised method for the estimation of heart rate variability (HRV) indices from ballistocardiograms (BCGs) recorded by a bed-mounted, electromechanical film (EMFi) sensor during sleep. After estimating the beat-to-beat intervals from the BCGs, short-term timeand frequency-domain HRV indices are computed and compared to an ECG reference. We evaluated signals record...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014