Social Distance and Face Mask Detection using vision-based sensors and IP cameras

Healthcare systems all over the world are strained as the COVID-19 pandemic's spread becomes more widespread. The only realistic strategy to avoid asymptomatic transmission is to monitor social distance, as there are no viable medical therapies or vaccinations for it. A unique computer vision-based framework that uses deep learning is to analyze the images that are needed to measure social distance. This technique uses the key point regressor to identify the important feature points utilizing the Visual Geometry Group (VGG19) which is a standard Convolutional Neural Network (CNN) architecture having multiple layers, MobileNetV2 which is a computer vision network that advances the-state-of-art for mobile visual identification, including semantic segmentation, classification and object identification. VGG19 and MobileNetV2 were trained on the Kaggle dataset. The border boxes for the item may be seen as well as the crowd is sizeable, and red identified faces are then analyzed by MobileNetV2 to detect whether the person is wearing a mask or not. The distance between the observed people has been calculated using the Euclidian distance. Pretrained models like (You only look once) YOLOV3 which is a real-time object detection system, RCNN, and Resnet50 are used in our embedded vision system environment to identify social distance on images. The framework YOLOV3 performs an overall accuracy of 95% using transfer learning technique runs in 22ms which is four times fast than other predefined models. In the proposed model we achieved an accuracy of 96.67% using VGG19 and 98.38% using MobileNetV2, this beats all other models in its ability to estimate social distance and face mask. © 2023 IEEE.

Efficient Centroid Based Distance Monitoring System Using Deep Learning

COVID-19 virus spread very rapidly if we come in contact to the other person who is infected, this was treated as acute pandemic. As per the data available at WHO more than 663 million infected cases reported and 6.7 million deaths are confirmed worldwide till Dec, 2022. On the basis of this big reported number, we can say that ignorance can cause harm to the people worldwide. Most of the people are vaccinated now but as per standard guideline of WHO social distancing is best practiced to avoid spreading of COVID-19 variants. This is difficult to monitor manually by analyzing the persons live cameras feed. Therefore, there is a need to develop an automated Artificial Intelligence based System that detects and track humans for monitoring. To accomplish this task, many deep learning models have been proposed to calculate distance among each pair of human objects detected in each frame. This paper presents an efficient deep learning monitoring system by considering distance as well as velocity of the object detected to avoid each frame processing to improve the computation complexity in term of frames/second. The detected human object closer to some allowed limit (1m) marked by red color and all other object marked with green color. The comparison of with and without direction consideration is presented and average efficiency found 20.08 FPS (frame/Second) and 22.98 FPS respectively, which is 14.44% faster as well as preserve the accuracy of detection. © 2023 IEEE.

Thermal Image Processing System for the measurement of body temperature using a Drone

In December 2019, several cases of pneumonia caused by SARS-CoV-2 were identified in the city of Wuhan (China), which was declared by the WHO as a pandemic in March 2020 because it caused enormous problems to public health due to its rapid transmission of contagion. Being an uncontrolled case, precautions were taken all over the world to moderate the coronavirus that undoubtedly was very deadly for any person, presenting several symptoms, among them we have fever as a common symptom. A biosecurity measure that is frequently used is the taking of temperature with an infrared thermometer, which is not well seen by some specialists due to the error they present, therefore, it would not represent a safe measurement. In view of this problem, in this article a thermal image processing system was made for the measurement of body temperature by means of a drone to obtain the value of body temperature accurately, being able to be implemented anywhere, where it is intended to make such measurement, helping to combat the spread of the virus that currently continues to affect many people. Through the development of the system, the tests were conducted with various people, obtaining a more accurate measurement of body temperature with an efficiency of 98.46% at 1.45 m between the drone and the person, in such a way that if it presents a body temperature higher than 38° C it could be infected with COVID-19. © 2023 IEEE.

Role of telemedicine in anesthesia: Are we ready yet?

Telemedicine is a modality which utilizes technology to provide and support health care across large distances. It has redefined the practices of medicine in many specialties and continues to be a boon for clinicians on many frontiers. Its role in the branch of anesthesia remains largely unexplored but has shown to be beneficial in all the three phases: pre-operative, intra-operative, and post-operative. Now time has come that anesthesiologists across the globe reassess their strategies and utilize the telemedicine facilities in the field of anesthesia.Copyright © 2021 EDP Sciences. All rights reserved.

Dr.'s Eye: The Design and Evaluation of a Video Conferencing System to Support Doctor Appointments in Home Settings

The spread of COVID-19 has encouraged the practice of using video conferencing for family doctor appointments. Existing applications and off-the-shelf devices face challenges in dealing with capturing the correct view of patients' bodies and supporting ease of use. We created Dr.'s Eye, a video conferencing prototype to support varying types of body exams in home settings. With our prototype, we conducted a study with participants using mock appointments to understand the simultaneous use of the camera and display and to get insights into the issues that might arise in real doctor appointments. Results show the benefits of providing more flexibility with a decoupled camera and display, and privacy protection by limiting the camera view. Yet, challenges remain in maneuvering two devices, presenting feedback for the camera view, coordinating camera work between the participant and the examiner, and reluctance towards showing private body regions. This inspires future research on how to design a video system for doctor appointments. © 2023 ACM.

IoT enabled Covid Standard Operating Procedure system

COVID-19, is caused by the transmission of SARS-CoV-2 through direct or indirect contact with infected people though respiratory droplets has transitioned from a pandemic to an endemic but is still regarded as active by WHO. Restrictions and lockdowns were lifted as the situation became endemic, but the previous measures had to be kept in place. By developing a module that includes temperature monitoring, face mask detection, a non-contact sanitizer dispenser, and door automation that operates based on the number of individuals inside a closed area in order to maintain social distance, our project aims to incorporate these precautions into our everyday language. As a part of making the new normal easily adaptable, we also introduce a webpagebased reservation system, which wm essentially display the current count and also help in reducing the waiting periods. © 2023 IEEE.

Resident Education on the Surgical Treatment of Distal Radius Fractures Using a Point-of-View Camera.

Background: In the coronavirus disease 2019 (COVID-19) era, surgical resident education depends largely on virtual materials. With the help of point-of-view (POV) cameras, educational videos have become widely used for surgical training. A video recorded from the surgeon's POV helps demonstrate the procedure. We made training movies of the surgical approach to distal radius fractures for residents using a head-mounted video recording system with a laser point targeting device (LPTD). Methods: A 15-minnute movie of the trans-flexor carpi radialis approach for distal radius fractures was made. A POV camera was assembled with an LPTD and strapped on the surgeon's head. This enabled maintenance of the surgical field while recording the procedure. A shorter version of the clip was also made to investigate trainee preference. We asked 24 trainees to watch the two versions of the video and complete a short questionnaire. Results: All trainees felt that the movie made with a POV camera was more efficient than existing materials. Only 1 (4.2%) felt that the laser pointer hindered the view. Four of the 23 trainees (16.7%) felt dizzy while watching the video. Of the two versions, 16 trainees (66.7%) preferred the shorter, edited version. The average score for the video was 8.42 out of 10. Conclusions: A video recording system in the operating room that uses an LPTD-POV camera is an efficient way to produce educational material, particularly for surgical residents during the COVID-19 era.

Drivers and Social Effects of the Decision to Turn on One?s Camera During Videoconferencing in Groups

With the emergence of the SARS-CoV-2 pandemic, videoconferencing was rapidly adopted. However, individuals frequently decide to keep their cameras off during videoconferences. Currently, the reasons for this are not well modeled, and neither are the social effects this decision has. The present research addresses the question whether camera use can be conceptualized as prosocial behavior. To this end, two preregistered studies (total N = 437) examined how the decision to turn on one's camera is influenced by established situational determinants (group size, social influence, and social tie strength) and dispositional predictors of prosocial behavior (individual communion, agency, and social value orientation), whether individuals prefer meetings in which others turn on their cameras, and whether camera use impacts social perception (communion and agency) by others. As predicted, people were shown to overall prefer meetings in which others turn on their cameras in Study 1 (a factorial survey). Furthermore, situational determinants of prosocial behavior were demonstrated to influence camera use in the hypothesized directions, while findings regarding dispositional predictors of prosocial behavior were mixed. Study 2 conceptually replicated the effect of social influence on camera use in a correlational survey. As predicted, it was also demonstrated that individuals who have their camera on are perceived as higher in agency, but, in contrast to predictions, not higher in communion. Together, the findings indicate that camera use is prosocial in that it benefits others, but that it is not primarily driven by prosocial intent or commonly interpreted as a prosocial act.

Comprehensive medication management services provided via telehealth or hybrid models: A scoping review

Comprehensive medication management (CMM) is increasingly provided by health care teams through telehealth or hybrid modalities. The purpose of this scoping literature review was to assess the published literature and examine the economic, clinical, and humanistic outcomes of CMM services provided by pharmacists via telehealth or hybrid modalities. This scoping review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews. Randomized controlled trials (RCTs) and observational studies were included if they: reported on economic, clinical, or humanistic outcomes;were conducted via telehealth or hybrid modalities;included a pharmacist on their interprofessional team;and evaluated CMM services. The search was conducted between January 1, 2000, and September 28, 2021. The search strategy was adapted for use in Medline (PubMed);Embase;Cochrane;Cumulative Index to Nursing and Allied Health Literature;PsychINFO;International Pharmaceutical s;Scopus;and grey literature. Four reviewers extracted data using a screening tool developed for this study and reviewed for risk of bias. Authors screened 3500 articles, from which 11 studies met the inclusion criteria (9 observational studies, 2 RCTs). In seven studies, clinical outcomes improved with telehealth CMM interventions compared to either usual care, face-to-face CMM, or educational controls, as shown by the statistically significant changes in chronic disease clinical outcomes. Two studies evaluated and found increased patient and provider satisfaction. One study described a source of revenue for a telehealth CMM service. Overall, study results indicate that telehealth CMM services, in select cases, may be associated with improved clinical outcomes, but the methods of the included studies were not homogenous enough to conclude that telehealth or hybrid modalities were superior to in-person CMM. To understand the full impact on the Quadruple Aim, additional research is needed to investigate the financial outcomes of CMM conducted using telehealth or hybrid technologies.Copyright © 2022 Pharmacotherapy Publications, Inc.

Technology-Driven Implementation of Smart Entrances in Public Places during the COVID-19

This research proposes a smart entrance system to cope with the COVID-19 pandemic in public places. The system can help automate standard operating procedures (SOPs) for checking. The paper focuses on exploring the problem context related to the COVID-19 SOPs for public places. The research on technologies involves using thermal cameras, fingerprint recognition, face recognition, iris recognition, object detection and cloud computing. These technologies can be integrated to provide a more versatile and effective solution. The technological solutions proposed by contemporary researchers are also critically analysed by investigating their advantages and disadvantages. © 2023 IEEE.

Design of VISUAL SLAM indoor disinfection robot based on STM32 control

In recent years, the novel corona virus pandemic is raging around the world, and the safety of home environment and public environment has become the focus of people's attention [2]. Therefore, the research on disinfection robot has become one of the important directions in the field of machinery and artificial intelligence. This paper proposes a robot with the STM32 MCU as the core of disinfection, and is equipped with a variety of sensors and a camera vision, has the original cloud service management platform, the remote deployment of navigation, based on visual SLAM to realize high precision navigation and positioning, can realize to indoor environment autonomously route planning, automatic obstacle avoidance checking, disinfection, epidemic prevention function, at the same time can pass Bit computer software realizes remote control of robot, which has great development potential. © 2022 ACM.

Online creative community support: Framing of two independent documentary films? creation from Caochangdi Workstation during the COVID-19 pandemic

In late December 2019, the world witnessed the outbreak of the novel coronavirus disease (COVID-19), which subsequently led to numerous social and work limitations including face-to-face communication and documentary production worldwide. While many studies have focused on the framing of COVID-19 by mainstream news agencies and political figures, few studies have concentrated on the perspectives of independent filmmakers regarding the pandemic. The challenges faced by these niche filmmakers during COVID-19 would have likely magnified and changed due to the uncertainties that befell filming and distribution. In this intrinsic case study, the researcher aims to explore the creative processes of two documentary films, Luo Luo's Fear and Entrapment, produced by emerging and experienced filmmakers, respectively, during the pandemic while participating in the Caochangdi (CCD) Workstation's Folk Memory Project. A qualitative thematic analysis was conducted on data collected from in-depth interviews with two participants and their reflective memos. This work also seeks to describe the filmmakers' experiences of filming during the pandemic and how these experiences framed their documentary filmmaking. Next, the researcher explores the salient visual framework used by the filmmakers through their documentary film analysis. Both films focused on their fears and challenges at this particular time of the pandemic, framing the entire film through internal monologues that have also become a distinctive style of their own creation. Overall, the current research contributes to the limited literature by focusing on the impacts of building of online strategies and creative community support on independent filmmakers' self-rescue during the pandemic and how visual framing can be enhanced in the study of films.

Design of illumination system using characterized illuminances for smartphone-based fundus camera.

Recently, smartphone-based fundus camera (SBFC) research has been actively conducted in response to the need to expand medical infrastructure in underdeveloped countries and the increased telemedicine since the COVID-19 pandemic. Compared to the conventional table-top system, SBFCs have technical challenges that make it difficult to guarantee uniform illumination and avoid back-reflection because of the design constraints of minimizing the form factor and cost. This paper proposes a novel illumination design methodology using characterized illuminance to obtain high-quality fundus images for SBFCs. Key performance indicators (KPIs), such as retinal uniformity, back-reflection suppression, and optical efficiency, were defined to evaluate the performance of the illumination system. Each KPI was calculated using optical simulation software based on Monte-Carlo ray tracing and mapped into a normalized three-dimensional coordinate, the retinal illumination performance space (RIPS). In RIPS, the KPIs are combined into a single parameter ΔRIPS, which is the quantitative difference evaluated as the Euclidean distance between the ideal and actual design point. A compact SBFC illumination system with five design variables was presented to verify the proposed methodology. The final design values at the minimum ΔRIPS were determined using the Taguchi method and response surface methodology. Finally, a working prototype was built, and fundus images were acquired by clinical testing under institutional review board approval. The fundus image had sufficient brightness and resolution to diagnose the lesion with a viewing angle of approximately 50° in one shot.

Evaluation of Hand Washing Procedure Using Vision-Based Frame Level and Spatio-Temporal Level Data Models

Hand hygiene is obligatory for all healthcare workers and vital for patient care. During COVID-19, adequate hand washing was among recommended measures for preventing virus transmission. A general hand-washing procedure consisting several steps is recommended by World Health Organization for ensuring hand hygiene. This process can vary from person to person and human supervision for inspection would be impractical. In this study, we propose computer vision-based new methods using 12 different neural network models and 4 different data models (RGB, Point Cloud, Point Gesture Map, Projection) for the classification of 8 universally accepted hand-washing steps. These methods can also perform well under situations where the order of steps is not observed or the duration of steps are varied. Using a custom dataset, we achieved 100% accuracy with one of the models, and 94.23% average accuracy for all models. We also developed a real-time robust data acquisition technique where RGB and depth streams from Kinect 2.0 camera were utilized. Results showed that with the proposed methods and data models, efficient hand hygiene control is possible.

Teledermoscopy-Aided Self-Skin Examinations for Remote Triage of Skin Lesions

Purpose of Study: Teledermatology, defined as the use of technology to provide dermatology services to individuals in a remote setting, has grown considerably in popularity since the onset of the COVID-19 era. Teledermoscopy utilizes a dermatoscope attachment paired with a smartphone camera to visualize colors and microstructures within the epidermis and superficial dermis that cannot be seen with the naked eye alone. When combined with store-and-forward technology, teledermoscopy of lesions concerning for skin cancer can improve virtual referral and triage workflow. Methods Used: Our retrospective case-control study evaluated the efficacy of a smartphone dermatoscope borrow program in the remote triage of individuals with self-selected skin lesions of concern and its effect on subsequent in-person follow-up visits. A retrospective medical record review was conducted of all Oregon Health and Science University (OHSU) Department of Dermatology spot check image submissions utilizing the smartphone dermatoscopes between August 2020-2022. Dermoscopic images of skin lesions that included corresponding non-dermoscopic clinical images in their submission were included in our review (n=70). A blinded expert dermoscopist then reviewed the clinical and dermoscopic images separately and utilized standard clinical algorithms for skin cancer (ABCD criteria: asymmetry, irregular borders, multiple colors, diameter>= 6mm for clinical images;3-point checklist: dermoscopic asymmetry, atypical network, blue-white structures for dermoscopy images) to determine whether the imaged lesion should translate to an in-person visit for further evaluation. Summary of Results: Of the 70 skin lesions submitted, 59 warranted in-person evaluation from clinical (non-dermoscopic) image review compared to 29 warranting in-person evaluation from dermoscopic images of the same lesion. Thus, this is a 51% reduction of conversion to in-person consultation with the addition of smartphone dermatoscope images in virtual lesion triage (P<0.001, McNemar's Test). Conclusion(s): Implementing patient-led teledermoscopy may reduce frequency of in-person visits for benign lesions, and thus, may decrease wait times for other patients with concerning and possibly malignant lesions. Decreasing the frequency of unnecessary visits may not only improve patient quality of life, but also promote cost-effective expenditures for health systems at large.

Session V

Novel cardiac monitoring technologies Chair: Jean-Philippe Couderc Jean-Philippe Couderc, University of Rochester, USA VPG/rPPG monitoring: Contactless cardiac monitoring using video cameras Saman Paravah, Edwards Lifesciences, USA Multiparameter physiological monitoring through smart wearables: current state and opportunities Konstantinos Rizas, Munich University of Medicine, Germany eBRAVE-AF Study Cederick Landry, University of Pittsburgh, USA Toward Smartphone-Based Blood Pressure Monitoring VPG/rPPG monitoring: Contactless cardiac monitoring using video cameras JP Couderc, PhD, MBAa,b a Cardiovascular Clinical Research Center, University of Rochester, Rochester, NY, United States of America b VPG Medical Inc., Rochester, NY, United States of America Background: In the post-COVID area, healthcare providers and patients have widely adopted telemedicine and telehealth tools. One of the limitations of these tools is to depend on patients' willingness to adopt home medical equipment to measure vital signs and other physiological information required by physicians for the diagnostic process, and sometimes for insurance coverage. Heart rate, blood pressure, SPO2, and the presence of cardiac arrhythmias are relevant, with 6 million people with AF in the U.S., and an estimated 700,000 individuals with undiagnosed AF. Video-based cardiac monitoring could represent a unique solution for telepatients with access to a camera at home (90% of the U.S. population). Method(s): We reviewed how video cameras from smart devices and computers have been used to provide cardiac monitoring outside the hospital. The method based on finger-based PPG measurements, or contactless facial photoplethysmographic (VPG) will be discussed in terms of measurement accuracy, detection performance, technological advantages, and limitations. We reviewed their accuracy for heart rate measurements, as well as their sensitivity, specificity, and negative and positive predictive values (NPV, and PPV) to detect the presence of abnormal pulsatile signals associated with AF rhythms. Result(s): The remote video-based technologies (rPPG/VPG) developed for cardiac monitoring have demonstrated excellent accuracy in extracting heart rate as well as a high level of sensitivity and specificity in detecting the presence of atrial fibrillation (sensitivity and specificity >90%). These measurement technologies are impacted by environmental and human factors requiring the technology to follow specific utilization constraints such as minimum level of environmental illumination (>50 lx). When used as a screening tool for a population with a low prevalence of AF, these methods reveal a low PPV (~30%). More recent studies evidence a PPV above 80% and NPV >90% when used as a monitoring tool in patients with a prior diagnosis of AF. Conclusion(s): There is increasing evidence that rPPG/VPG monitoring technologies provide medical-grade functionalities. Their monitoring performances especially for AF detection remain to be demonstrated in studies involving large cohorts of patients.Copyright © 2023

Control and Monitoring of Thermographic Chambers by Means of PLC and HMI

Covid-19 disease affects the individual's body in different ways. Most of the infected people present various symptoms of complexity. This article develops the design of a system of control and monitoring of people through the use of thermographic cameras, which includes an intelligent control system for the detection of people with symptoms of Covid-19, which at the same time allows estimating a reading of parameters obtained from the thermographic camera, the possible suspected cases of people entering the Continental University. The development of the proposed system will allow obtaining real-time data of each user entering the Continental University, these parameters obtained will be stored in a SQL database that is linked to an HMI screen where the temperature of each person is displayed, if in case they exceed the established temperature ranges, instant access to the facility is restricted. The results of the research showed that the system design contributes to the prevention and mass propagation of Covid-19. © 2022 IEEE.

Covid -19 Social Distance Analysis Using Machine Learning

According to the Ministry of Global Health, social distance is one of the most effective defenses against COVID-19 and helps to prevent its spread. Governments have imposed many safety orders on citizens and facilities to limit social distancing and slow the spread of the virus. As a result, there has been an increase in interest in technologies to research and control the spread of COVID-19 in various settings. This research aims to investigate the results of several machine learning approaches to find cases when the physical distance between people has been violated. The method first identifies the instance of the human in the video frame, tracks the movements, computes the distance with other humans on the same frame and thus estimates the number of people who violate the social distance. Compares the approach to performing the performance using Yolo, SSD and Faster R- CNN. Videos that are used in this approach are collected from the wild, considering different camera settings, indoor and outdoor scenes, and recorded from various angles. Comparing the three methods Yolo, SSD and Faster RNN, the results show Yolo has a better performance in detecting humans from the current videos and thus in determining the violation of the distance between humans. © 2023 IEEE.

FedCare: Federated Learning for Resource-Constrained Healthcare Devices in IoMT System

In social IoMT systems, resource-constrained devices face the challenges of limited computation, bandwidth, and privacy in the deployment of deep learning models. Federated learning (FL) is one of the solutions to user privacy and provides distributed training among several local devices. In addition, it reduces the computation and bandwidth of transferring videos to the central server in camera-based IoMT devices. In this work, we design an edge-based federated framework for such devices. In contrast to traditional methods that drop the resource-constrained stragglers in a federated round, our system provides a methodology to incorporate them. We propose a new phase in the FL algorithm, known as split learning. The stragglers train collaboratively with the nearest edge node using split learning. We test the implementation using heterogeneous computing devices that extract vital signs from videos. The results show a reduction of 3.6 h in the training time of videos using the split learning phase with respect to the traditional approach. We also evaluate the performance of the devices and system with key parameters, CPU utilization, memory consumption, and data rate. Furthermore, we achieve 87.29% and 60.26% test accuracy at the nonstragglers and stragglers, respectively, with a global accuracy of 90.32% at the server. Therefore, FedCare provides a straggler-resistant federated method for a heterogeneous system for social IoMT devices.

Near Real-Time Social Distance Estimation In London

To mitigate the current COVID-19 pandemic, policy makers at the Greater London Authority, the regional governance body of London, UK, are reliant upon prompt, accurate and actionable estimations of lockdown and social distancing policy adherence. Transport for London, the local transportation department, reports they implemented over 700 interventions such as greater signage and expansion of pedestrian zoning at the height of the pandemic's first wave with our platform providing key data for those decisions. Large well-defined heterogeneous compositions of pedestrian footfall and physical proximity are difficult to acquire, yet necessary to monitor city-wide activity (busyness) and consequently discern actionable policy decisions. To meet this challenge, we leverage our existing large-scale data processing urban air quality machine learning infrastructure to process over 900 camera feeds in near real-time to generate new estimates of social distancing adherence, group detection and camera stability. In this work, we describe our development and deployment of a computer vision and machine learning pipeline. It provides near immediate sampling and contextualization of activity and physical distancing on the streets of London via live traffic camera feeds. We introduce a platform for inspecting, calibrating and improving upon existing methods, describe the active deployment on real-time feeds and provide analysis over an 18 month period.