Dhanush Reddy K N, Darshan B, Ganagalla Jeevan Kumar
Dhanush Reddy K N, Darshan B, Ganagalla Jeevan Kumar
Dhanush Reddy K N, Darshan B, Ganagalla Jeevan Kumar
12 (2021), 2200-2206
Research Article
Social Distance Monitoring And Face Mask Detection System For Covid-19
Pandemic
Dhanush Reddy K N1, Darshan B2, Ganagalla Jeevan Kumar3, Gopi Krishna R4, Nitya
S5
1
School of Electronics and Communication Engineering, REVA University, (INDIA)
2
School of Electronics and Communication Engineering, REVA University, (INDIA)
3
School of Electronics and Communication Engineering, REVA University, (INDIA)
4
School of Electronics and Communication Engineering, REVA University, (INDIA)
5
School of Electronics and Communication Engineering, REVA University, (INDIA)
Article History: Received: 11 January 2021; Revised: 12 February 2021; Accepted: 27 March 2021; Published
online: 23 May 2021
Abstract: In this time when COVID-19 is spreading rapidly, it is essential to maintain social distance and wearing a mask is
compulsory and to avoid large public gatherings at one place to break the chain of corona infection. But maintaining this is
not easy. Many people, knowingly or unknowingly, gather and roam on the streets without wearing a mask. Keeping an eye
fixed on of these activities isn't a simple job. The authorities need reliable technology to keep track of these activities. This
Project can help in monitoring the social distance and also it detects face mask. This whole system is placed in Public
gatherings, traffic signals, on roads and also at the entrance of schools and college gates. This system uses a Raspberry Pi
with an RPi camera for capturing live video. The video is then processed frame-by-frame. By using image processing with
the help of TensorFlow and OpenCV people, vehicles in the video and are identified. First, it detects the presence of the
crowd and then with the help of object tracking algorithm and distance algorithm the centroid distances from one person to
another person is measured if the distance is violated it gives an alert and by using Keras, OpenCV and Mobilenet people
without a mask are detected when this happens it gives alert by speaking.
Keywords: COVID-19, Keras,OpenCV, Raspberry-Pi, TensorFlow
1. Introduction
COVID-19 belongs to the family of coronavirus caused diseases, initially reported at Wuhan, China, in late
December 2020. On March 11, it covers 114 countries with 118,000 active cases and 4000 deaths, WHO
declared this a pandemic[1],[2]. On November 18, 2020, over 54,771,888 cases and 1,324,249 deaths had been
reported worldwide. The second wave of covid in 2021 April became severe and rise in the cases, as of now it is
reported 141 million cases causing 3 million deaths worldwide. Several healthcare organizations, doctors and
scientists try to develop proper medicines and vaccines for this deadly virus, but to date, no success is reported.
This situation forces the worldwide community to seem for alternate ways to prevent the spread of this infectious
virus. Social distancing is claimed because the best spread stopper within the present scenario and everyone
affected countries are locked down to implement social distancing. This research is aimed to support and
mitigate the coronavirus pandemic along with side minimum loss of economic endeavours, and propose an
answer to detect the social distancing among people gathered at any public place. The word social distancing is
best practice within the direction of efforts through a spread of means, getting to minimize or interrupt the
transmission of COVID-19. It aims at reducing the physical contact between possibly infected individuals and
healthy persons. As per the WHO norms[3], it is prescribed that people should maintain at least 1 meter of
distance from each other in order to follow social distancing. A recent study indicates that social distancing is a
crucial containment measure and essential to stop SARS -CoV-2 because people with mild or no symptoms may
fortuitously carry corona infection and can infect others[4],. Fig. 1 indicates that proper social distancing is that
the best thanks to reducing infectious physical contact, hence reduces the infection rate[5],[6]. This reduced peak
may surely match with the available healthcare infrastructure and help to supply better facilities to the patients
battling against the coronavirus pandemic.
2200
Turkish Journal of Computer and Mathematics Education Vol.12 No.12 (2021), 2200-2206
Research Article
Fig.1:-An outcome of social distancing as the reduced peak of the epidemic and matching with available
healthcare capacity.
This virus can be affected from human to human through droplets and airborne. According to the instruction
from WHO, to reduce the spread of COVID-19, every people need to wear a face mask, do social distancing,
evade the crowd area and also always maintain the immune system. Therefore, to protect each other, every
person should wear the face mask properly when they are outdoor. However, most selfish people won’t wear the
face mask properly for so many reasons. People wear masks partially covering their nose and mouth and this is
also detected by the camera.
2. Literature survey
Social distancing is surely the most trustworthy technique to stop the spreading of infectious disease, with
this belief, in the background of December 2019, when COVID-19 emerged in Wuhan, China, it was opted as an
unprecedented measure on January 23, 2020[7] . Within one month, the outbreak in China gained a peak in the
first week of February with 2,000 to 4,000 new confirmed cases per day. Later, for the first time after this
outbreak, there have been a sign of relief with no new confirmed cases for five consecutive days up to 23 March
2020[8]. This is evident that social distancing measures enacted in China initially, adopted worldwide later to
control COVID-19.
Prem et al[9]. aimed to study the effects of social distancing measures on the spread of the COVID-19
epidemic. Authors used synthetic location-specific contact patterns to simulate the ongoing trajectory of the
outbreak using susceptible-exposed-infected-removed (SEIR) models. It was also suggested that premature and
sudden lifting of social distancing could lead to an earlier secondary peak, which could be flattened by relaxing
the interventions gradually. As we all understand, social distancing though essential but economically painful
measures to flatten the infection curve.
Adolph et al[10]. highlighted the situation of the United States of America, where due to lack of common
consent among all policymakers it could not be adopted at an early stage, which is resulting into on-going harm
to public health. Although social distancing impacted economic productivity, many researchers are trying hard to
overcome the loss. Following from this context, Kylie et al[11]. studied the correlation between the strictness of
social distancing and the economic status of the region. The study indicated that intermediate levels of activities
could be permitted while avoiding a massive outbreak.
Since the novel coronavirus pandemic began, many countries have been taking the help of technology based
solutions in different capacities to contain the outbreak[12],[13],[14]. Many developed countries, including India
and South Korea, for instance, utilising GPS to track the movements of the suspected or infected persons to
monitor any possibility of their exposure among healthy people. In India, the government is using the
ArogyaSetu App, which worked with the help of GPS and bluetooth to locate the presence of COVID-19 patients
in the vicinity area. It also helps others to keep a safe distance from the infected person[15].
Single Shot Detector architecture is used for the object detection purpose. In this system face mask detector
can be deployed in many areas like shopping malls, airports and other heavy traffic places to monitor the public
and to avoid the spread of the disease by checking who is following basic rules and who is not.It takes excessive
time for data loading in Google Colab Notebook. It did not allow the access of webcam which posed a hurdle in
testing images and video stream.We have modeled a facemask detector using Deep learning. We are processed a
system computationally efficient using MobileNetV2 which makes it easier to Extract the data sets. We use CNN
architecture for better performance. We can fix it in any kind of cameras.
Human beings have not tremendous ability to identify different faces than machines, so automatic face
detection system plays an important role in face recognition,head- pose estimation etc.It has some problems like
face occlusion, andnon uniform illumination. We use Neural Network to detect face in the Live video stream.
Tensor flow is also used in thissystem . In existing they use Adaboost algorithm, we are using mob net CNN
Architecture model in our proposed system.We will overcome all these problems in this paper.
The following hardware and software components are used during development, designing and testing
phases.
2201
Turkish Journal of Computer and Mathematics Education Vol.12 No.12 (2021), 2200-2206
Research Article
Hardware requirements:
➢ Raspberry Pi 3
➢ Raspberry pi Camera
➢ Power Adapter
➢ Speaker
➢ Connecting wires
➢ Power supply
Software requirements:
➢ Rasbian
➢ Python IDLE
➢ Tensor flow
➢ Open CV
➢ Keras
➢ VNC Viewer
4. Proposed methodology
The main aim of this project is to detect the crowd if the crowd is detected it measures the distance between
the people in the crowd and also detects face masks of the people in the crowd. This system uses a Raspberry Pi
with an RPi camera for capturing live video. The video is then processed frame-by-frame. By using image
processing with the help of TensorFlow and OpenCV people, vehicles in the video and are identified. With the
help of an object tracking algorithm and distance algorithm, the centroid distances from one person to another
person is measured if the distance is violated it gives an alert. and by using Keras, OpenCV and Mobilenet
people without mask and also partially wore masks were detected when this happens it gives alert by speaking.
Let’s have a brief how these algorithms work
• F = (P * D)/W
• D’=(W * F)/P
2202
Turkish Journal of Computer and Mathematics Education Vol.12 No.12 (2021), 2200-2206
Research Article
P – How much pixel the image covered
W- Width of the Image
D- Distance between the camera and image
With the help of above equations we can calculate the distance between two persons.
5. Block diagram
2203
Turkish Journal of Computer and Mathematics Education Vol.12 No.12 (2021), 2200-2206
Research Article
2204
Turkish Journal of Computer and Mathematics Education Vol.12 No.12 (2021), 2200-2206
Research Article
7. Conclusion
An effective solution to make sure COVID-19 safety compliance is presented during this work. As we know
COVID-19 is a deadly disease it is advised to follow some precautionary measures such as Social distancing and
wearing a mask is compulsory. But people are neglecting this, here comes our model to keep track of the
people.This system uses raspberry pi with a Raspberry pi camera which is cost-effective and can be implemented
anywhere such as shopping complexes, metro stations, Airports etc. and also this system can assist police by
minimizing their physical surveillance work in containment zones and public areas where surveillance is
required employing camera feeds with raspberry pi in real-time. Thus, this proposed system will operate
efficiently in the current situation when the lockout is eased and helps to track public places easily in an
automated manner. We have addressed thorough the tracking of social distancing and therefore the identification
of face masks that help to make sure human health. The implementation of this solution was successfully tested
in real-time by deploying the model in raspberry pi3. The solution has the potential to significantly reduce
violations by real-time interventions, so the proposed system would improve public safety by saving time and
helping to reduce the spread of corona virus.
References
1. World Health Organisation. WHO Corona-viruses Disease Dashboard (August 2020). Available at
2. https: //covid19.who.int/table
3. WHO Director, Generals. Opening remarks at the media briefing on COVID-19 (2020).WHO
generals and directors speeches.
4. L. Hensley, “Social distancing is out, physical distancing is inheres how to do it,” Global News–
Canada (27 March 2020), 2020.
5. ECDPC, “Considerations relating to social distancing measures in response to COVID-19 second
update,” https://www.ecdc.europa.eu/en/publicationsdata/considerations, 2020, [Online; accessed
March 23, 2020].
6. M. W. Fong, H. Gao, J. Y. Wong, J. Xiao, E. Y. Shiu, S. Ryu, and B. J. Cowling,
“Nonpharmaceutical measures for pandemic influenza in nonhealthcare settings social distancing
measures,” 2020.
7. F. Ahmed, N. Zviedrite, and A. Uzicanin, “Effectiveness of workplace social distancing measures in
reducing influenza transmission: a systematic review,” BMC public health, vol. 18, no. 1, p. 518,
2018.
8. B. News, “China coronavirus: Lockdown measures rise across Hubei province,”
9. https://www.bbc.co.uk/news/world-asia-china51217455, 2020, [Online; accessed January 23, 2020].
10. N. H. C. of the Peoples Republic of China, “Daily briefing on novel coronavirus cases in China,”
11. http://en.nhc.gov.cn/2020-03/20/c 78006.htm, 2020, [Online; accessed March 20, 2020].
12. K. Prem, Y. Liu, T. W. Russell, A. J. Kucharski, R. M. Eggo, N. Davies, S. Flasche, S. Clifford, C.
A. Pearson, J. D. Munday et al., “The effect of control strategies to reduce social mixing on
2205
Turkish Journal of Computer and Mathematics Education Vol.12 No.12 (2021), 2200-2206
Research Article
outcomes of the covid19 epidemic in wuhan, china: a modelling study,” The Lancet Public Health,
2020.
13. C. Adolph, K. Amano, B. Bang-Jensen, N. Fullman, and J. Wilkerson, “Pandemic politics: Timing
state-level social distancing responses to covid-19,” medRxiv, 2020.
14. K.E. Ainslie, C. E. Walters, H. Fu, S. Bhatia, H. Wang, X. Xi, M. Baguelin, S. Bhatt, A.
Boonyasiri,O. Boyd et al., “Evidence of initial success for china exiting covid-19 social distancing
policy after achieving containment,” Wellcome Open Research, vol. 5, no. 81, p. 81, 2020.
15. S. K. Sonbhadra, S. Agarwal, and P. Nagabhushan, “Target specific mining of covid-19 scholarly
articles using one-class approach,” 2020.
16. N. S. Punn and S. Agarwal, “Automated diagnosis of covid-19 with limited posteroanterior chest x-
ray images using fine-tuned deep neural networks,” 2020.
17. N. S. Punn, S. K. Sonbhadra, and S. Agarwal, “Covid-19 epidemic analysis using machine learning
and deep learning algorithms,” medRxiv, 2020.[Online]. Available:
https://www.medrxiv.org/content/early/2020/04/11/2020.04.08.2005767
18. REVISION OF MODELS AND FUNCTIONALITIES IN DATA MINING PROCESS,
S.Sivasakthi, International Journal Of Advance Research In Science And Engineering
http://www.ijarse.com IJARSE, Volume No. 10, Issue No. 04, April 2021 ISSN-2319-8354(E).
19. O. website of Indian Government, “Distribution of the novel coronavirus-infected
pneumoniAarogyaSetu Mobile App,”https://www.mygov.in/aarogya-setu
2206