Measuring the pulse rate by using webcam

Full text

MEASURING THE PULSE RATE BY USING WEBCAM
R.Archana, M.Lakshmi Raviteja
Under the guidance of Prof. Dr. Zacharaiah Alex,
M.tech, Sensor systems technology, School Of Electronics Engineering,
VIT UNIVERSITY, Vellore-632014, India
rallapalli.archana2013@vit.ac.in
Abstract – In this paper a simple method for determining
the physiological parameters of the face of different
subjects using basic Logitech webcam was introduced.
The physiological pulse waves were extracted from
imaging PPG systems. The IR light is focussed on the
non-contact surface whose influence gives a relationship
between ambient light intensity and the normalised PPG
Signals. This provides the pulse rate and the heart rate by
means of practical non-contact physiological assessment
with labview software.
Keywords— Photoplethysmography (PPG), IR led,
ambient light, non-contact, webcam, labview,
I. I
NTRODUCTION
Photoplethysmography (PPG), was first described in the
year 1930s,[1] is a simple, low-cost, and non-invasive
optical technique through variations in the transmitted or
reflected ambient light, which is used to measure the
blood volume changes that occur in man, due to the
pulsatile nature of the circulatory system..The peripheral
pulse acquired from photoplethysmography (PPG) can
provide information about cardiovascular status, such as
blood oxygen saturation, heart and respiration rates,
cardiac output, and blood pressure [2].
PPG is a signal which is typically implemented using
dedicated light sources (e.g., red or infrared wavelengths)
with normal ambient light as the illumination source [3]
on the non- contact surface of the human body.
In this Paper, a robust method is implemented by digital
color video recordings of the human face [4] is
implemented from which the continuous pulses from the
human face are attained
offering reliable assessment of the
cardiovascular
system during rest, at motion and after
exercise and therefore develops a PPG Signal. This signal
acquisition
technique is based on a webcam and using
ambient
IR
light illumination. This is a noncontact method
that can detect
the heart-generated pulse wave and can be
used as a flexible noncontact PPG system that introduced a
camera based
multiple wavelength imaging PPG device that
provides
a potential route towards contactless assessment of
blood oxygen
saturation, have reported a webcam-based
technique
for remote acquisition of PPG signals that uses
ambient
light as a source of illumination.[5]
These examples
Indicate two research streams in imaging PPG are as follows:
high-definition, camera-based imaging PPG (iPPG) and
webcam-based imaging PPG, its practicability and reliability
in terms of remote assessment of the cardiovascular system
has been shown have been set up to compare the reliability
and sensitivity of ambient light-based imaging PPG[6],
Measurements in accessing the cardiovascular system
Measurements were taken from subjects undergoing various
intensities of exercise in order to make these comparative
assessments under different physiological conditions.
II.METHODOLOGY
A. System Architecture:
The test device consists of a Logitech webcam of resolution
1280 x 1024 pixels which is kept close to the non-contact
surface of the human body that is the face. The distance
between the camera and face was approximately 350 mm. The
ambient IR light has to be focussed on the non-contact face.
The person is to be tested and all equipment was positioned in
a room with no artificial light present. During the cardiac
cycle, some volumetric changes in the facial blood vessels
modify the path length of the incident ambient light such that
the changes in amount of reflected light indicate the timing of
cardiovascular events. By recording a video of the facial
region with a webcam, the red, green, and blue (RGB) color
sensors pick up a mixture of the reflected plethysmographic
signal along with other sources of fluctuations in light due to
different artifacts [6].
Figure 1. System model.
Non-
Contact
Face
IR Light Web
Cam Labview PPG

B. Sensor Design
In this paper we are using a Logitech Webcam with
maximum pixel resolution of 1280x1024. The experiment
was conducted only indoors and with a varying amount of
ambient sunlight entering through windows as the only
source of illumination.[8] During the experiment, the
person was asked to keep still and breathe correspondingly
and face the webcam while their video was recorded for
one minute using Vision Acquisition block in Labview
software. All videos were recorded in color of range (24-
bit RGB with three channels × 8 bits/channel) at 30 frames
per second (fps)with a pixel resolution of 640 × 480.
The recordings were taken with the person at many stages
of positions like rest and motion, firstly at rest to minimize
motion and those of the second were taken with the person
performing various intensities of exercise [9]. Hence, the
current study employed individual image-processing
procedures for each instant of action. Specifically, a spatial
averaging approach was first conducted to generate the
reduced frames for the experiment [10].
All the video and physiological recordings were analyzed
using custom software written in Labview called NI Vision
Acquisition. Fig. 1 provides an overview of the stages
involved in our approach to recover the PPG from the
webcam videos. We utilized the NI Vision library [12] to
automatically identify the coordinates of the face location
in the first frame of the video recording.
The Sample PPG which is to be obtained will be as
follows:
Figure 2: Sample PPG signals at rest and motion
The above figure in the paper shows the PPG of the same
person at different stages of action like rest and motion.
The main part of the sensor here is the Logitech Webcam,
which works on the basis of the sensing mechanism as the
contact sensor.
The face is the target for remote detection
because it is uncovered during the exercise/motion, and it has
been known that the facial PPG.
signal is typically stronger than that from other anatomical
locations of the body during the non-contact measurement.
For the video recording using NI Vision Acquision Block
in Labview software was used. The person was asked to
move naturally with his face pointing directly toward the
direction of camera, along with focusing the IR light on the
facial surface where the camera is kept in the contact. Care
has to be taken that the person has to be remained seated
and to maintain planar alignment of his face with the
camera during the motion and rest positions. Images of
512×512 pixels were taken from the face at a lower frame
rate (30 fps, Texposure = 40 ms) [13] to allow image
capture over an increased duration of exercise (1min).
The distance between the camera lens and the face was
~300 mm.
Separate plethysmographic Waveforms obtained from each
of these two functions rest and motion by calculating the
related pulse rate for each minute. This complete apparatus
is interfaced with Labview software using vision
acquisition by the following code consisting of Colored
histogram for the analysis of image in the red plane.
III.PROGRAMMING AND ANALYSIS
This complete apparatus described above is now
interfaced with NI Labview software using vision
acquisition by the following code consisting of Colored
histogram for the analysis of image in the red plane.
In the displayed NI Labview program, the captured
images are continuous and may also be considered as
video recording configured through obtained RGB image
and the distortions are removed by using the Filters.
Figure 3: NI Labview code

The obtained continuous video is taken after the focussing
light from the led to the non-contact and recorded from
the camera, after interfacing with Vision acquisition
occurs as follows:
Figure 4: Red Image after interfacing
It is know interfaced to NI labview by using NI Vision
acquisition block and configuring the frame rate as 30fps,
by creating a while loop by itself. The output image
which comes as the out come of the NI Vision acquisition
is now given to the colour histogram for the formation of
the image in the RED plane. This image after connecting
to the colour histogram gives the minimal value, maximal
value, starting value of the waveform, interval width of
the waveform, Mean value of the all the intensities, which
gives the average number of pulses per minute, standard
deviation and the Area(pixels) of the pulse waveform.
The average mean value was calculated by the calculating
the product of the area (pixels) and the obtained mean
value. This value is compared with a constant to make the
comparison in between the on and off conditions, and to
know the values of Ton and Toff approximately.
IV. RESULTS
The obtained waveform is the PPG which is analysed for the
calulation of average pulses is as follows:
This PPG gives different values for different persons,
depending on the motion of the body and varies accordingly,
when the person is in rest and motion. The below shown is the
PPG signal when the person is in rest.
Figure 5:Graphical representation of the obtained PPG
signal
Observations:
Two different types of PPG signals are measured and
observed when the person is in rest and motion. Both the PPG
signals are almost 97% accuracy and are similar to each other.
The apparatus used is well optimized and compatible
.
The mean value that is the approximate pulse rate per minute
here is 148 at rest and is 137 when in motion. The area
(pixels), mean value, frame rate are indicated in the below
labview VI.
This complete analysis is now shown as follows:
Figure 6: Complete Analysis
Discussion:
The IR light from the IR led is focussed on the non-
contact face of the human body. The Logitech 9000
webcam is placed closed to the non-contact face with a
maximum resolution and the imaging is now interfaced to
the NI labview, a VI is created in labview which consists of
NI Vision acquisition through which the video of the led
focused non-contact face is acquired and is analysed by the
corresponding labview program using color histogram and

clusters. All the above explains about the occurrence and
analysing of the obtained PPG.
V. CONCLUSION
The measurement of the pulse rate using the ordinary
webcam is simpler and has got many applications. This
device can be used in analysing the problems like suffering
from high blood pressure and also used in the pulse
oximetry. The advantages of this monitoring apparatus are:

Sports and triage training.

Meausring the physiological parameters like
heart/respiratory rate, tissue blood perfusion and arterial
oxygen saturation distributions).
 Demonstrate a strong correlation in between the
parameters derived from webcam recordings and
standard reference sensors.
VI. REFERENCES
1.
YuSun, Sijung Hu, Vicente, Azorin-Peris, Motion-
compensated noncontact imaging
photoplethysmography to monitor cardio respiratory
status during exercise.
2.
Journal of Bio-medical optics by Stephen Greenwald,
Jonathon Chambers, Yisheng Zhu.
3.
Ming-Zher Poh, Daniel J. McDuff, and Rosalind W.
Picard Advancements in Noncontact, Multiparameter
Physiological Measurements Using a Webcam.
4.
Roy Kalawsky, Vicente Azorin-Peris, Use of ambient
light in remote photoplethysmographic
systems:comparison between a high-performance
camera and a low-cost webcam.
5.
“Photoplethysmography and its application in
clinical physiological measurement,” Physiol. Meas.
28(3), R1–39 (2007).
J. Allen,
6.
Biomed. Eng., vol. 54, no. 8, pp. 1418–1426, Aug.
2007, M. Garbey, N. Sun, A. Merla, and I. Pavlidis,
“Contact-free measurement of cardiac pulse based on
the analysis of thermal imagery,” IEEE Trans
7.
Heart rate variability: Standards ofmeasurement,
physiological interpretation, and clinical use,” Eur.
Heart J., vol. 17, pp. 354–381, M. Malik, J. Bigger,
A. Camm, R. Kleiger, A. Malliani, A. Moss, and P.
Schwartz, “1996
8.
Development of non-contact monitoring system of
heart rate variability hrv)-an approach of remote
sensing for ubiquitous technology,” in Proc.Int.
Conf. Ergonom. Health Aspects Work Comput., San
Diego, CA, 2009,S. Suzuki, T. Matsui, S. Gotoh, Y.
Mori, B. Takase, and M. Ishihara,
9.
Opt. Expr., vol. 18, pp. 10762–10774, May 2010 M.
Z. Poh, D. J. McDuff, and R. W. Picard, “Non-
contact, automated
cardiac pulse measurements using video imaging
and blind source separation,”
10.
Contact-free measurement of heart rate variability
via a microwave sensor,” Sensors, vol. 9, pp. 9572–
9581, 2009
.
11.
Physiol. Meas.31(5), 715–726 (2010), L. Wang, C.
C. Y. Poon, and Y. T. Zhang, “The non-invasive
andcontinuous estimation of cardiac output using a
photoplethysmogram and electrocardiogram during
incremental exercise,”
12.
“Noncontact simultaneous dual wavelength
photoplethysmographya further step toward
noncontact pulse oximetry,” Rev. Sci. Instrum. 78(4),
044304 (2007).K. Humphreys, T. Ward, and C.
Markham.
13.
Ann. Biomed. Eng. 33(8),1034–1041 (2005), F. P.
Wieringa, F. Mastik, and A. F. W. van der Steen,
“Contactless multiple wavelength
photoplethysmographic imaging: a first step toward
'SpO(2) camera' technology
,”