A team of researchers developed an AI-empowered video surveillance system used to observe and inform social distancing breaches without compromising privacy.They demonstrated it by keeping image processing gated to a local network of cameras, thereby outdoing the necessity to store sensitive data in a central server.
They conducted the case study at Gold Coast Airport which, pre-COVID-19 had 6.5 million passengers annually with 17,000 passengers on-site daily. Hundreds of cameras cover 290,000 square meters with hundreds of shops and more than 40 check-in points. Experimenters lightweight and cutting-edge algorithms for efficient performance.
“Our goal was to create a system capable of real-time analysis with the ability to detect and automatically notify airport staff of social distance.”
Three out of nine cameras were used to detect automatic social distance breach detection in the check-in area, food court and waiting area. Two people were employed to compare live video feeds and the AI analysis results to determine if people marked as red were in breach. Researchers found camera angles affect the ability of AI to detect and track people’s movements in a public area and recommend angling cameras between 45 to 60 degrees.
The AI-enabled surveillance system provides accurate results by reducing data bias and improving transparency in how the system works.