DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic

Abstract

Social distancing is a recommended solution by the World Health Organisation (WHO) to minimise the spread of COVID-19 in public places. The majority of governments and national health authorities have set the 2-m physical distancing as a mandatory safety measure in shopping centres, schools and other covered areas. In this research, we develop a hybrid Computer Vision and YOLOv4-based Deep Neural Network (DNN) model for automated people detection in the crowd in indoor and outdoor environments using common CCTV security cameras. The proposed DNN model in combination with an adapted inverse perspective mapping (IPM) technique and SORT tracking algorithm leads to a robust people detection and social distancing monitoring. The model has been trained against two most comprehensive datasets by the time of the research—the Microsoft Common Objects in Context (MS COCO) and Google Open Image datasets. The system has been evaluated against the Oxford Town Centre dataset (including 150,000 instances of people detection) with superior performance compared to three state-of-the-art methods. The evaluation has been conducted in challenging conditions, including occlusion, partial visibility, and under lighting variations with the mean average precision of 99.8% and the real-time speed of 24.1 fps. We also provide an online infection risk assessment scheme by statistical analysis of the spatio-temporal data from people’s moving trajectories and the rate of social distancing violations. We identify high-risk zones with the highest possibility of virus spread and infection. This may help authorities to redesign the layout of a public place or to take precaution actions to mitigate high-risk zones. The developed model is a generic and accurate people detection and tracking solution that can be applied in many other fields such as autonomous vehicles, human action recognition, anomaly detection, sports, crowd analysis, or any other research areas where the human detection is in the centre of attention.

Contributions of Smart City Solutions and Technologies to Resilience against the COVID-19 Pandemic: A Literature Review

“…Related to prediction capabilities, smart solutions have also been used to identify hotspots and risky public spaces that are essential for implementing targeted measures and policies [2,46]. In Tokyo, a chatbot-based health care support system named COOPERA was developed to collect large-scale information on the pandemic situation using a smart phone messenger application named LINE.…”

“…Geographical distribution of these symptoms showed strong spatial correlation between respondents with symptoms and the cumulative number of confirmed cases, indicating that large scale monitoring using chatbot-based systems can be used as an effective method for understanding the pandemic situation and identifying infection hotspots in cites [47]. Similarly, Rezaei and Azarmi [46] developed a hybrid computer vision and deep neural network (DNN) model to automatically detect people in urban public spaces using CCTV security cameras. Using the spatio-temporal dataset of people's movement trajectories of Oxford's town center to evaluate the model, they demonstrated the utility of the model for identifying urban spaces that are not conducive to maintaining social distancing and that are likely to make it difficult to control the spread of the virus.…”

“…Using the spatio-temporal dataset of people's movement trajectories of Oxford's town center to evaluate the model, they demonstrated the utility of the model for identifying urban spaces that are not conducive to maintaining social distancing and that are likely to make it difficult to control the spread of the virus. Identification of these potentially high-risk areas helps planners and designers to redesign the structure of open and public spaces to make them more pandemic-proof [46].…”

A Vision-Based Social Distancing and Critical Density Detection System for COVID-19

“…Furthermore, there is no implementation or privacy-related discussion other than the violation index. Another work [6] developed a DNN model called DeepSOCIAL for people detection, tracking, and distance estimation. In addition to social distancing monitoring, it also performed dynamic risk assessment.…”

“…Vision-based automatic detection and control systems [2][3][4][5][6][7][8][9] are economic and effective solutions to mitigate the spread of COVID-19 in public areas. Although the conceptualization is straightforward, the design and deployment of such systems require smart system design and serious ethical considerations.…”