Research Outline

Physical Distancing Technologies

Goals

Preliminary research on physical distancing technologies in relation to COVID-19, including mobile, IoT devices, software, and hardware.

Early Findings

Here we present our preliminary research on physical distancing technologies in relation to COVID-19, from the simplest solution all the way through mobile apps and wearable devices to the most complex IoT software and hardware technologies.

e-token

  • Local markets and small vendors can ensure physical distancing and avoid crowding by sending a link to email-registered market users. Clicking on this link generates an e-token with a number that informs the users of their places in the queue. By checking a link provided in the email, the user can check the status of their token and go to the market to pick up their orders.

APPs-based

mContain

  • This app uses location and Bluetooth technologies in smartphones to detect proximity encounters with other app users. The app counts and displays the number of daily proximity encounters with other app users, similar to a step count. This reduces the chance of entering a crowded place by map displaying. Furthermore, if a user and his/her COVID-19 test provider agree to share the results of the test, the app can notify other users about potential coronavirus exposure.

Crowdless

  • This app uses anonymized existing data sources, such as Google Maps and Google Places data, tracking the movements of mobile devices. The app combines tracking satellite information with Artificial Intelligence (AI) by asking users to confirm how busy the location is so that users can maintain social distancing and avoid crowds.

6 Feet Away

  • A free Apple iOS app uses Augmented Reality to show how far to stay away from other people for safe physical distancing purposes.

Software-based

Voxel51

  • This software platform uses advanced machine learning and an index called the Physical Distancing Index (PDI). PDI detects the average density of human activity from public live web streams using cutting-edge computer vision technology, thus measuring and ensuing physical/social distancing.

Devices

Virus Defended Distance Reminder Smart Wristband

  • This is a new wristband that is customized to control a social distance in the real workplace by means of sensors technology. When two people come closer to 1.5 - 2 meters, the wristband will send a warning signal by flashing or vibration.

Triax Proximity Device

  • This is contact tracing and physical distancing solution to be deployed in the workplace by means of a proximity trace device that is attached to a hard hat. This Internet of Things (IoT) based solution helps to keep workers safe and avoid the spread of the coronavirus.

Sonarax

  • Sonarax uses the speaker and microphone that is present in every smartphone, mobile phone, tablet, laptop, PC, cash register, vending machine, digital signage, etc., to transmit and receive data over Sound Waves instead of radio waves, measuring distance, duration & data and ensuring social distancing.

BriefCam

  • BriefCam studies the interactions between people and the objects in their environment for tracing infected individuals’ contact with their surroundings using advanced multi-camera video searches and accurate face-recognition Deep Learning techniques.

Complete-solutions

Pervasive

  • This comprehensive solution uses ideal thermal equipment, software, cloud, and AI applications to conduct remote screenings of human temperature, proximity detection, and facial personal protection recognition for health & safety purposes.

Smart City Technology

  • This solution consists of an urban data dashboard that applies social distancing measures on people and vehicle movement within a metropolitan city in real-time. It makes use of thousands of sensors and data sharing agreements to monitor movement around the city, from traffic and pedestrian flow to congestion, car park occupancy, and bus GPS trackers. Furthermore, it monitors energy consumption, air quality, climate, and many other variables analyzing a billion individual pieces of observational data, as well as other data sources, combined with Deep Learning algorithms.