Cameras that sync with one another to track suspects

Electrical engineers from the University of Washington in the Us have developed a way to automatically track people across moving and still cameras by using a technology that trains the networked cameras to learn one another's differences.

The cameras first identify a person in a video frame then follow that same person across multiple camera views.

The linking technology can be used anywhere as long as the cameras can talk over a wireless network and upload data to the cloud.

This detailed visual record could be useful for security and surveillance, monitoring for unusual behaviour or tracking a moving suspect.

"Tracking humans automatically across cameras in a 3D space is new. As the cameras talk to each other, we are able to describe the real world in a more dynamic sense," said Jenq-Neng Hwang, lead researcher and professor of electrical engineering.

The tracking system first systematically picks out people in a camera frame, then follows each person based on his or her clothing texture, colour and body movement.

An algorithm automatically applies those differences between cameras and can pick out the same people across multiple frames, effectively tracking them without needing to see their faces.

With the new technology, a car with a mounted camera could take a video of a scene, then identify and track humans and overlay them into the virtual 3D map on your GPS screen.

"Our idea is to enable the dynamic visualisation of the realistic situation of humans walking on the road and sidewalks, so eventually people can see the animated version of the real-time dynamics of city streets on a platform like Google Earth," Hwang added.

The researchers are developing this to work in real time. This could help pick out people crossing busy intersections or track a specific person who is dodging the police.

They also installed the tracking system on cameras placed inside a robot and a flying drone, allowing the robot and drone to follow a person, even when the cameras came across obstacles that blocked the person from view.

Hwang and his research team presented the results at the "Intelligent Transportation Systems Conference" in Qingdao, China, recently.