Automated Face Mask Detection using Artificial Intelligence and Video Surveillance Management

Surveillance camera has become an essential, ubiquitous technology in people's daily lives, whether applicable for home surveillance or extended to public workplace detection. The importance of the camera is irreplaceable in terms of the agent for an enclosed system to function correctly. The goal of ubiquitous computing is to keep different devices or technology communicating seamlessly, allowing them to expand to other areas instead of limiting it to one device. However, many research papers have been released on how the camera can aid in the current situation where COVID-19 is still raging worldwide, especially in crowded places. This paper aims to suggest a method by which surveillance cameras on the university campus can automatically detect student face mask status and notify them. Alongside that, this concept of applying a video management system within the university campus will assist in the automation of invigilating the student's daily mask status from the number of embedded surveillance cameras around the campus. © 2023 IEEE.

Views and Needs of Students, Parents, and Teachers on Closed-Circuit Television, Proximity Trackers, and Access Cards to Facilitate COVID-19 Contact Tracing in Schools: Thematic Analysis of Focus Groups and Interviews.

BACKGROUND: Contact tracing is considered a key measure in preventing the spread of infectious diseases. Governments around the world adopted contact tracing to limit the spread of COVID-19 in schools. Contact tracing tools utilizing digital technology (eg, GPS chips, Bluetooth radios) can increase efficiency compared to manual methods. However, these technologies can introduce certain privacy challenges in relation to retention, tracking, and the using and sharing of personal data, and little is known about their applicability in schools. OBJECTIVE: This is the second of two studies exploring the potential of digital tools and systems to help schools deal with the practical challenges of preventing and coping with an outbreak of COVID-19. The aim was to explore the views, needs, and concerns among secondary school stakeholders (parents, teachers, pupils) regarding the implementation of three digital tools for contact tracing: access cards, proximity tracking, and closed-circuit television (CCTV). METHODS: Focus groups and interviews were conducted with secondary school students, parents, and teachers. The topic guide was informed by the Unified Theory of Technology and Acceptance. Data-driven and theory-driven approaches were combined to identify themes and subthemes. RESULTS: We recruited 22 participants. Findings showed that there is no single solution that is suitable for all schools, with each technology option having advantages and limitations. Existing school infrastructure (eg, CCTV and smart/access cards technology) and the geography of each school would determine which tools would be optimal for a particular school. Concerns regarding the cost of installing and maintaining equipment were prominent among all groups. Parents and teachers worried about how the application of these solutions will affect students' right to privacy. Parents also appeared not to have adequate knowledge of the surveillance technologies already available in schools (eg, CCTV). Students, who were mostly aware of the presence of surveillance technologies, were less concerned about any potential threats to their privacy, while they wanted reassurances that any solutions would be used for their intended purposes. CONCLUSIONS: Findings revealed that there is not one tool that would be suitable for every school and the context will determine which tool would be appropriate. This study highlights important ethical issues such as privacy concerns, balancing invasions of privacy against potential benefits, transparency of communication around surveillance technology and data use, and processes of consent. These issues need to be carefully considered when implementing contact tracing technologies in school settings. Communication, transparency, and consent within the school community could lead to acceptance and engagement with the new tools.

AI-based traffic counting: A Case Study in Vietnam

Ho Chi Minh City, particularly Vietnamese cities in general, is so busy and crowded since tremendous numbers of motorbikes move on roads. Ho Chi Minh City leaders have encountered several challenges in fully understanding and effectively dealing with problems of urban traffic for the past few decades. Software-based solutions are proper and dramatically necessary, currently. This paper presents the deployment of an AI-based application at the Ho Chi Minh City Department of Transportation. The paper mainly concentrates on traffic counting problems during the outbreak of the Covid-19 pandemic from June 2021. The performance of the AI-based application was compared with medical declaration data and achieved an accuracy of 93.80%. © 2022 IEEE.

Counting Number of People and Social Distance Detection Using Deep Learning

With its enormous spread, the continuing COVID-19 corona virus pandemic has become a worldwide tragedy. Population vulnerability rises as a result of fewer antiviral medicines and a scarcity of virus fighters. By minimizing physical contact between people, the danger of viral propagation can be reduced. Previously, the distance between two individuals, as well as the number of people breaching the distance, could be computed with alarm. In the proposed methodology, including the existing features in the previous methodology and additionally, the total number of people present in a given frame, as well as the number of people who were violated,non-violated are tallied. The most crucial step in improving social separation detection is to use proper camera calibration. It will produce better results and allow you to compute actual measurable units instead of pixels It can also figure out how many people are in a certain location. As a result, the suggested system will be useful in identifying, counting, and alerting persons who are breaching the specified distance, as well as estimating the number of people in the frame to manage corona spread. © 2022, IFIP International Federation for Information Processing.

Thermal Screening Solution Using Infrared Thermography and Closed-Circuit Television

Closed-circuit television camera (CCTV) and thermal imaging devices are used to detect febrile individuals entering establishments for Coronavirus 2019 (COVID-19) containment. Real-time tracking in post-COVID is manually checked by security personnel, which has risks of less efficiency due to human errors, as advance thermal cameras are unaffordable for some business owners. The main goal is converting an installed CCTV interfaced with infrared sensor to develop an economical thermal screening system with acoustic alarm. In this project, the colored and heatmap images transmitted from the thermal camera were processed through OpenCV. A calibration method was also performed to validate the temperature reading from the thermal camera. The project comes with graphical user interface (GUI) connected into a database, which visually tracks individuals exhibits elevated body temperature. The performance of the system shows above 95% accuracy upon conducting an inexpensive calibration check. The significance of this project is highlighting the effective mitigation of virus spread which offers safe and contactless analysis of potential individuals showing early symptoms of COVID-19. Additional features can be added for future work such as facemask detector, multiple thermal camera setup, and Login Options making the device and application exclusively for business owners. © 2022 IEEE.

Seeing is believing? A systematic review of credibility perceptions of live and remote video-mediated communication in legal settings

There has been a dramatic increase in use of remote communication via audio-visual technology since the COVID-19 pandemic. This includes use in complex legal hearings where decisions rely heavily on credibility assessments of an individual and their interview statement. This is particularly relevant in legal settings where negative assessments can have adverse outcomes such as asylum applications which can result in deportation. Increasing use of remote communication technology raises the question of what research can tell us about how someone is perceived when interviewed live (in-person) compared with via video-mediation. A systematic review of the literature resulted in the selection of nine papers. Four themes were identified;decision-maker's assumptions, frame of the camera, demeanour and detecting truth and lies. The results are discussed within the context of credibility judgements in asylum proceedings together with implications for further research and practice. Copyright © 2022 The Authors. Applied Cognitive Psychology published by John Wiley & Sons Ltd.

Face Recognition at varying angles from distant CCTV Footage using Siamese Architecture

Face Recognition is a deeply studied and researched domain. There are quite large solutions and model architectures to tackle majority of the face recognition related concerns. In this work we come up with a more specific version of face recognition which can mainly be used to achieve long distance and natural limitations of CCTV identification in real world scenarios using existing methods to better modifications. The solution which paper proposes using deep learning can be used to recognise a person even if they wear face masks due to the Covid-19 pandemic. One-shot learning is incorporated which can be used to train the specific model with just one image per person of the individual to be recognized. The designed model is modified from Siamese network architecture trained in triplet loss function to achieve these requirements. © 2022 IEEE.

Application of CCTV Methodology to Analyze COVID-19 Evolution in Italy.

Italy was one of the European countries most afflicted by the COVID-19 pandemic. From 2020 to 2022, Italy adopted strong containment measures against the COVID-19 epidemic and then started an important vaccination campaign. Here, we extended previous work by applying the COVID-19 Community Temporal Visualizer (CCTV) methodology to Italian COVID-19 data related to 2020, 2021, and five months of 2022. The aim of this work was to evaluate how Italy reacted to the pandemic in the first two waves of COVID-19, in which only containment measures such as the lockdown had been adopted, in the months following the start of the vaccination campaign, the months with the mildest weather, and the months affected by the new COVID-19 variants. This assessment was conducted by observing the behavior of single regions. CCTV methodology allows us to map the similarities in the behavior of Italian regions on a graph and use a community detection algorithm to visualize and analyze the spatio-temporal evolution of data. The results depict that the communities formed by Italian regions change with respect to the ten data measures and time.

Real-time passenger social distance monitoring with video analytics using deep learning in railway station

Recently, at the end of December, the world faced a severe problem which is a pandemic that is caused by coronavirus disease. It also must be considered by the railway station's authorities that it must have the capability of reducing the covid transmission risk in the pandemic condition. Like a railway station, public transport plays a vital role in managing the COVID-19 spread because it is a center of public mass transportation that can be associated with the acquisition of infectious diseases. This paper implements social distance monitoring with a YOLOv4 object detection model for crowd monitoring using standard CCTV cameras to track visitors using the deep learning with simple online and real-time (DeepSORT) algorithm. This paper used CCTV surveillance with the actual implementation in Bandung railway station with the accuracy at 96.5% result on people tracking with tested in real-time processing by using minicomputer Intel(R) Xeon(R) CPU E3-1231 v3 3.40GHz RAM 6 GB around at 18 FPS. © 2022 Institute of Advanced Engineering and Science. All rights reserved.

CrowdSurge: A Crowd Density Monitoring Solution Using Smart Video Surveillance with Security Vulnerability Assessment

—Overcrowding and crowd density monitoring in various places and establishments are being implemented since the pandemic, which helps observe social distancing. This study is about the development of a crowd density solution by utilizing YOLOv4 and Closed-Circuit Television (CCTV) called CrowdSurge. The practice of CCTV has been around for so many years with proven benefits. This has been combined with the state-of-the-art YOLOv4 algorithm that provides high video analytics and object detection performance. With the combination of the said technology and algorithm, it will serve as a smart surveillance system. A system and mobile application have been developed, and the YOLOv4 deep learning detection model was used to detect various set of scenarios considered to assess if the model executes according to the actions assigned in the experimental set-up. The browser-based application was tested using CVSS or Common Vulnerability Scoring system, which shows that the severity level of most vulnerabilities is low and has a minor impact on the system. Based on the overall usability testing and statistical results, the respondents are satisfied with both surveillance system and mobile applications developed in terms of functionality, usefulness, and aesthetics. Therefore, using the developed system in real-time surveillance can aid in crowd density reduction in an area. © 2022.

Crowd Analysis of Almasjid Alnabawi using convolutional neural networks of CCTV footage

In recent months, crowd management has become more important than ever, given the spread of contagious diseases such as COVID-19. The Hajj, in Saudi Arabia, is one of the largest gatherings in the world;it happens annually and is getting bigger every year. The development of radio-frequency identification (RFID) and mobile apps has been investigated to help estimate crowd movements in and among the holy sites. However, network-based technologies require large infrastructures and are therefore very costly. In this paper, a system is proposed to use existing closed-circuit television (CCTV) to accurately visualize the movements of crowds in the Almasjid Alnabawi, also known as The Prophet's Mosque. The proposed neural network is trained with large datasets of crowd images to produce estimates of the number of pilgrims in an image. Images are then integrated to produce crowd level models throughout the building. The system has been tested on two instances and showed high performance.

A Deep Learning Based Social Distance Analyzer with Person Detection and Tracking Using Region Based Convolutional Neural Networks for Novel Coronavirus

With its staggering spread, the continuous novel coronavirus Covid flare-up has caused a worldwide disaster. Populace weakness develops because of an absence of productive helpful prescriptions and a shortage of antibodies against the infection. Since there are no antibodies accessible as of now, social detachment is viewed as a sufficient insurance (standard) against the transmission of the illness. With the ascent in cases, the public authority has ordered a base actual division of 2 meters in all open spaces as a security measure. Utilizing PC vision on video reconnaissance, we made an AI device to forestall the spread of the (novel coronavirus). A social separating analyzer AI apparatus that utilizes video observing from CCTV cameras and robots to control social removing convention. The made AI device was introduced in broad daylight spaces and guaranteed the distance between gatherings of individuals. If the hole was excessively close, the red line showed up, demonstrating a higher danger of being influenced, trailed by the green and yellow light, showing a protected line, and the other, demonstrating a generally safe of being influenced. © 2022 River Publishers.