Researchers at US universities are creating a new laser-based system for autonomous vehicles (AVs) that can image around corners in real-time.

On further development, the laser-based system might allow autonomous vehicles to ‘look’ around parked cars or busy intersections in order to detect hazards.

This system could also have the potential to be installed on satellites and spacecraft for tasks such as capturing images inside an asteroid cave.

Stanford University and Rice University research team leader Christopher Metzler said: “Compared to other approaches, our non-line-of-sight imaging system provides uniquely high resolutions and imaging speeds.

“These attributes enable applications that wouldn’t otherwise be possible such as reading the license plate of a hidden car as it is driving or reading a badge worn by someone walking on the other side of a corner.”

The new system can also differentiate sub-millimeter level details of a hidden object from 1m away.

It can image small objects at high resolutions and can be combined with other imaging systems that generate low-resolution reconstructions. Sorry, there are no polls available at the moment.

The new system uses a camera sensor and a powerful but standard laser source. As the laser beam hits a wall and bounces off onto the hidden object and back onto the wall, it creates a speckle pattern that indicates the shape of the hidden object.

In order to reconstruct the hidden object from the speckle pattern, there is a need to solve a challenging computational problem.

Although short exposure times are necessary for real-time imaging, such procedures produce too much noise for existing algorithms to work. To address this problem, the researchers turned to deep learning.

The researchers, whose study was published in Optica journal, tested a new technique by reconstructing images of 1cm-tall letters and numbers hidden behind a corner using an imaging set-up about 1m from the wall.

They used an exposure length of a quarter of a second, which in turn produced reconstructions with a resolution of 300 microns.

This research is part of DARPA’s Revolutionary Enhancement of Visibility by Exploiting Active Light-fields (REVEAL) programme.

The team is now working to make the system practical for more applications.