Police car equipped with facial recognition system can pick suspects out of a crowd

March 28, 2016 - 

Researchers at the University of Electronic Science and Technology of China’s Police Equipment Joint Research Lab have developed a police vehicle equipped with a facial recognition system that can pick criminal suspects out of a crowd, according to a report by the Wall Street Journal.

State media reports that the SUV has a 360-degree rooftop camera array that automatically scans faces within a 60-meter radius. The system determines the gender, age and race of each face, compares it against faces stored in the police database and alerts the driver if a match is made. Similar to licence plate readers, the system works even while traveling at speeds of up to 120 kilometers per hour (75mph).

Aside from scanning people’s faces, the surveillance system also detects vehicle information and identifies mobile phones within its radius.

“As long as you get at least three-quarters of the face, you can make an ID,” Yin Guangqiang, director of the Police Equipment Joint Research Lab, told state media. He added that the system can also recognize license plate numbers and car types, and can be set to scan for just “one type of person.”

“The new car is not just a means of transportation,” said Guangqiang. “It is more like a smart law enforcement system on wheels.”

The vehicle is scheduled to be road-tested in Hangzhou when the coastal city hosts the G-20 Summit in September.

Last November, the UAE’s Ministry of Interior began testing a similar facial recognition system in a moving patrol car to automatically capture the faces of pedestrians and compare those images to images of wanted suspects stored in a police database.

Leave a Comment

comments

About Stephen Mayhew

Stephen Mayhew is the publisher and co-founder of Biometrics Research Group, Inc.. His experience includes a mix of entrepreneurship, brand development and publishing. Stephen attended Carleton University and lives in Toronto, Canada. Connect with Stephen on LinkindIn.