Face Mask Detection using Single Shot Multibox Detector and Mobile Net

During the pandemic time government took many safety measures to protect the public at common gathering places. People are insisted on wearing a face mask to protect themselves from COVID. Even then many people were roaming without a mask in public places. The proposed technique to detect the face mask is to identify the person's face with mask and person's face without mask and reporting to the safety officers about the persons without mask for further action. The proposed Face mask detection is developed using the ML technique which can be used to classify the people wearing masks and not wearing masks with the input given to the model. The proposed face mask detector is a one-stage detector that focuses on detecting the face mask alone. This work is implemented using the Tensor flow and Computer vision libraries. NumPy is used for image processing. The data set used in MAFA dataset. The model is trained using this data set to get the accurate results. To enable multiple detection here the single shot with multi box detector is used. The base model used for this process is Mobile Net V2. The proposed model is simple and it can be integrated with several other technologies to provide high accuracy percentage of output in the minimum possible time. © 2022 IEEE.

Intelligent Real-Time Face Mask and Temperature Recognition Using Deep Learning on Raspberry Pi

There has been a steady and significant growth of the advancement in computer vision systems for face masks and temperature tracking. The World Health Organization introduce strict measures to prevent the spread of the coronavirus disease. This paper attempts to create a highly accurate and real-time approach that can effectively detect non-mask trying to enforce to wear mask in order to contribute to community health. For the purpose of detecting face masks, a hybrid model combining deep and regular machine learning will be utilized. We will use OpenCV to recognize faces in real time from a live feed via the Camera module using a dataset that includes images with and without masks and send the data to the cloud for visualization and further analysis. As a main part of the solution, we proposed embedded system with tools utilizing Python, OpenCV, and Tensor Flow with using computer vision and deep learning. To make it cost efficient, quick, scalable, and effective the whole process for detection of face mask is carried out on Raspberry Pi. This project enables improved control over the information already provided and strongly points out the deployment of our method to stop the local transmission from spreading and decrease the possibility of human coronavirus disease carriers. © 2022 IEEE.

Primary Contacts Identification for COVID-19 Carriers from Surveillance Videos

COVID-19 (Coronavirus disease of 2019) is caused by SARS-CoV2 (Severe Acute Respiratory Syndrome Coronavirus 2) and it was first diagnosed in December 2019 in China. As of 25th Aug 2021, there are 165 million confirmed COVID-19 positive cases and 4.4 million deaths globally. As of today, though there are approved COVID-19 vaccine candidates only 4 billion doses have been administered. Until 100% of the population is safe, no one is safe. Even though these vaccines can provide protection against getting seriously ill and dying from the disease, it does not provide 100% protection from getting infected and passing it on to others. The more the virus spreads;it has more opportunity to mutate. So, it is mandatory to follow all precautions like maintaining social distance, wearing mask, washing hands frequently irrespective of whether a person is vaccinated or not. To prevent spread of the virus, contact tracing based on social distance also becomes equally important. The work proposes a solution that can help with contact tracing/identification, knowing the infected persons recent travel history (even within the city) for few days before being assessed positive. While the person would be able to give the known contacts with whom he/she has interacted with, he/she will not be aware of who all were in proximity if he/she had been in public places. The proposed solution is to get the CCTV (Closed-Circuit Television) video clips from those public places for the specific date and time and identify the people who were in proximity-i.e., not followed the safe distance to the infected person. The approach uses YOLO V3 (You Only Look Once) which uses darknet framework for people detection. Once the infected person is located from the video frames, the distance from that person to the other people in the frame is found, to check if there is a violation of social distance guideline. If there is, then the people violating the distance are extracted and identified using Facial detection and recognition algorithms. Two different solutions for Face detection and Recognition are implemented and results compared-Dlib based models and OpenCV (Open Source Computer Vision Library) based models. The solutions were studied for two different CCTV footages and the results for Dlib based models were better than OpenCV based models for the studied videos. © 2022 CRL Publishing. All rights reserved.

Mask and emotion: Computer vision in the age of COVID-19

Computer vision systems since the early 1960s have undergone a long evolution and are widely used in various fields, in particular, in education for the implementation of immersive educational resources. When developing computer vision systems for educational purposes, it is advisable to use the computer vision libraries based on deep learning (in particular, implementations of convolutional neural networks). Computer vision systems can be used in education both under normal and pandemic conditions. The changes in the education industry caused by the COVID-19 pandemic have affected the classic educational applications of computer vision systems, modifying existing ones and giving rise to new ones, including social distancing, face mask recognition, intrusion detection in universities and schools, and vandalism prevention, recognition of emotions on faces with and without masks, attendance monitoring. Developed on the basis of Microsoft Cognitive Toolkit and deployed in the Microsoft Azure cloud, a prototype computer vision system integrates emotion recognition of students and detection of violations of the mask regime, additionally providing the ability to determine gender, smile intensity, average age, makeup, glasses, hair color, etc. with a high degree of reliability. © 2021 ACM.

COVID-19: Automatic Social Distancing Rule Voilation Detection using PP-Yolo Tensorflow in OpenCV

In this critical situations where people are fighting with dangerous pandemic disease;it is required to maintain the situation by indulging with social distancing or it can also be pronounced as physical distancing. Social or physical distancing may reflects to reduce the virus from spreading. There are several places where it should be followed properly to stop spreading COVID-19 like railway stations, malls, marts, airports and many more. It is advised to maintain at least 6 feet of social distancing as per the WHO guidelines. Various researches have been done to automatically detect the physical distancing violations but an ideal system should be available to detect it effectively with high level of accuracy. Here the system is based on PP-Yolo (PaddlePaddle - You only look once) and Tensorflow library. Tensorflow is an object detection or pattern recognition tool through which pedestrian can be detected automatically and then PP-Yolo classifies the distance between the pedestrians or classifying whether persons are following the physical distancing rule or not. Violation detection is bit challenging for any system because a crowd may have uncertain structures that can hardly classified distance among them. This challenge can be accepted through various researchers but not met the desired precision. Proposed system is intended to detect the physical distancing rule violations effectively and acquiring high level of accuracy with minimal false alarm rate. © 2022 IEEE.

Vision-Based Hand Tracking System Development for Non-Face-to-Face Interaction

Human-computer interaction (HCI) focuses on the interaction between humans and computers and it exists ubiquitously in our daily lives, especially in post COVID era where non-face-to-face interaction is common. Since HCI usually uses a physical controller such as a mouse or a keyboard, it hinders National User Interface, giving a middle ground between the user and the computer. This paper presents a vision-based hand tracking system development for non-face-to-face interaction, which aims to improve HCI by being able to track the hand which will act as the pen and functioning as a reusable writing surface for creating texts, drawings, and such as well as removing or erasing using the user's hand as the pen, and utilizing Open Computer Vision Library (OpenCV) and Mediapipe. Using the computer's camera the hand will be tracked as the pen for creating basic drawings and handwriting. The vision-based board where the user can draw on and the pen or marker will be the user's hand. The results indicate that this system is accurate enough to be a feasible application for handwriting ad basic drawings. © 2021 IEEE.