Using Visual-AI to Highlight COVID-19 Lockdown Violations in Italy
BLOG

Using Visual-AI to Highlight COVID-19 Lockdown Violations in Italy

Spotting COVID-19 Lockdown violations on social media

More and more countries are tightening their rules around movement and physical distance to help mitigate the spread of COVID-19. While most of us are doing all we can to support this effort during the COVID-19 Lockdown, social media has been littered with posts of people ignoring their health ministries’ advice and regulations, causing distress to citizens, health workers and government officials all the world over.

Italy is one of the worst affected areas in the world and, despite this, many of the country’s citizens did not initially follow the government’s decree, putting more lives at risk.

VISUA’s co-founders, Luca Boschin and Alessandro Prest are Italian citizens, as are many of the company’s employees, seeing news reports of Italians posting photos on social media showing them ignoring the lockdown rules was a source of great worry and distress. They decided to do something about it.

They spent some time looking at how VISUA’s technology could be put to practical use to help reduce the spread of COVID-19. They ultimately merged a number of AI modules typically used for brand monitoring, and applied it in collaboration with Ghost Data, to a set of anonymised data to identify the level and types of violations during the initial period of the lockdown.

Download a Copy of COVID-19 Lockdown Report

Instagram lockdown violations

Using Public Data and Visual AI to Identify COVID-19 Lockdown Violations

In collaboration with Ghost Data, the CEO of which, Andrea Stroppa, is also Italian, VISUA sought to understand the volume risk and behaviours of the local population in this state of crisis through the use of big data analysis and image and video recognition technology.

This study harvested images and video from 552,000 profiles and their public Instagram stories (totalling 504,592 stories), covering the period from March 11th to March 18th, 2020.

The data was anonymised as it was gathered and prior to processing. This meant stripping out any personal data, such as profile information, decreasing geo-location precision, blurring faces and removing metadata that could be used to identify individuals.

Group 2_Covid 19 lockdown location map

What The Report Revealed

  1. 50% of people not conforming to quarantine were taking part in group activities
  2. 40% of Italians not confirming were in the city, while 26% were spending time at the beach and 17% were out in parks and parkland
  3. The highest levels of quarantine violations were in the regions of Lombardy, Campania, Sicily and Lazio

Our Hopes For This Report

We hope this staggering data will encourage people, wherever they are in the world, to follow the advice set out by the World Health Organization, as well as the rules put in place by their country’s governments. Stay safe.

Download a Copy of the Report

RELATED

BLOG
VISUA News: Franco De Bonis Interviews With Safety Detectives

VISUA Marketing director discusses Visual-AI in cybersecurity with Aviva Zacks Aviva Zacks of Safety Detectives reached out to our own Franco De […]

Anti-Phishing Cybersecurity VISUA News
BLOG
Podcast: Visual-AI DIY? Are You Crazy?

A Poke in The AI – Episode 1 – Visual-AI DIY? Are You Crazy? Introducing the Visual-AI podcast you’ve been waiting for! […]

Technology VISUA News
BLOG
Press Release: Introducing VISUA On-Device Deployment

PRESS RELEASE VISUA On-Device Deployment Takes World-Leading Visual-AI To Places It Couldn’t Go Before VISUA’s new On-Device implementation enables key applications for […]

VISUA News

Trusted by the world's leading platforms, marketplaces and agencies

Integrate Visual-AI Into Your Platform

Seamlessly integrating our API is quick and easy, and if you have questions, there are real people here to help. So start today; complete the contact form and our team will get straight back to you.

  • This field is for validation purposes and should be left unchanged.