Monitoring Social Distancing Using Artificial Intelligence for Fighting COVID-19 Virus Spread

Monitoring Social Distancing Using Artificial Intelligence for Fighting COVID-19 Virus Spread

Hashem Alyami, Wael Alosaimi, Moez Krichen, Roobaea Alroobaea
Copyright: © 2021 |Pages: 16
DOI: 10.4018/IJOSSP.2021070104
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

To restrict COVID-19, individuals must remain two meters away from one another in public since public health authorities find this a healthy distance. In this way, the incidence of “social distancing” keeps pace with COVID-19 spread. For this purpose, the proposed solution consists of the development of a tool based on AI technologies which takes as input videos (in real time) from streets and public spaces and gives as output the places where social distancing is not respected. Detected persons who are not respecting social distancing are surrounded with red rectangles and those who respect social distancing with green rectangles. The solution has been tested for the case of videos from the two Holy Mosques in Saudi Arabia: Makkah and Madinah. As a novel contribution compared to existent approaches in the literature, the solution allows the detection of the age, class, and sex of persons not respecting social distancing. Person detection is performed using the Faster RCNN with ResNet-50 as it is the backbone network that is pre-trained with the open source COCO dataset. The obtained results are satisfactory and may be improved by considering more sophisticated cameras, material, and techniques.
Article Preview
Top

1. Introduction

The coronavirus has spread around the world, causing panic around the planet: thousands of new cases and hundreds of deaths are announced every day. Many cities - and entire countries - are on lockdown, with flight cancellations, international events and annual festivals. Europe has become the new epicenter of the disease, while elsewhere - in Latin America, the United States and the Middle East - the infection rate is increasing daily.

Several Asian countries, despite their geographical proximity to China (where the disease started), are showing the way forward to curb the rate of COVID-19 infection. These countries have succeeded in dealing with the spread of the coronavirus because they acted quickly and implemented innovative policies (Meuwese (2020); Moradian et al. (2020)):

The World Health Organization (WHO) and experts in the field agree that early detection (Chu et al. (2020)) is a fundamental factor in containing the spread of the pandemic (Altman, Mounir, Najid, and Perlaza (2020)). Countries that have relied on testing have seen the number of new cases drop, while countries where testing (Ghaffari, Meurant, and Ardakani (2020)) has not been implemented have seen the number of cases rise sharply.

People with a high temperature are sent to “fever clinics” (Kong et al. (2020)) and tested for influenza or COVID-19. If they test positive for COVID-19, they are isolated in what has been dubbed “quarantine hotels” (Baum and Goh (2021)) to avoid infecting their families, neighbors, and friends. Once the disease is already in a country, containment measures are no longer valid. In this situation, the most effective way to protect the public is to quickly implement social distancing (Aquino, Silveira, Pescarini, Aquino, and Souza-Filho (2020); Courtemanche, Garuccio, Le, Pinkston, and Yelowitz (2020); Pedersen and Favero (2020); Thunstrom, Newbold, Finnoff, Ashworth, and Shogren (2020)) - as has been demonstrated in Hong Kong and Taiwan. In Hong Kong, people have been told to work from home, close schools and cancel all social events.

In this work, our ultimate goal was to contribute to the development of techniques which facilitate social distancing measures in order to minimize the transmission of the COVID-19 virus by reducing contact between sensitive subjects and infected people. The reduction of the disease propagation will in turn lead to the reduction of the number of deaths due to this virus. By reducing the number of infected persons the public and private hospitals will be able to continue working in a quasi-normal circumstances since the total load of work and the number of patients will still remain under the maximum capacities of these institutions. Reducing the number of people infected and the number of deaths will also save a lot of money and avoid large financial losses.

With numerous positive stories, artificial intelligence (AI) has been widely implemented in our everyday lives in a number of areas such as digital multimedia tampering detection for forensics analysis (Bourouis, Alroobaea, Alharbi, Andejany, and Rubaiee (2020)), the recognition of lung diseases in chest X-rays images (Alharithi, Almulihi, Bourouis, Alroobaea, and Bouguila (2021)), and facial expression recognition (Najar et al. (2020)). Artificial intelligence has also made a significant contribution to addressing the pandemic of coronavirus disease (COVID-19), which currently occurs around the world. In the battle against the deadly COVID-19 epidemic many AI techniques have been used in various applications. These techniques outline the crucial roles of AI research in this fight (Chamola, Hassija, Gupta, and Guizani (2020); Hussain, Bouachir, Al-Turjman, and Aloqaily (2020); Mushtaq et al. (2021); Vaishya, Javaid, Khan, and Haleem (2020); N. Zheng et al. (2020)).

The main objectives of this work may be summarized as follows:

  • 1.

    Providing efficient techniques for detecting people violating social distancing rules;

  • 2.

    Identifying the sex and age class of the persons violating these rules.

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 14: 1 Issue (2023)
Volume 13: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 1 Issue (2015)
Volume 5: 3 Issues (2014)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing