Enlarge

ACD May 30, 2021

British researchers are working on an augmented reality heads-up display capable of seeing through objects.

British researchers have developed the first LiDAR-based augmented reality display for use in vehicles. Tests with a prototype version of the technology suggest that it could improve road safety by “seeing through” objects to alert to potential dangers without distracting the driver.

The technology, developed by researchers at the University of Cambridge, University of Oxford and University College London (UCL), is based on LiDAR (Light Detection and Range) and uses LiDAR data to create ultra high definition holographic renderings of road objects which are transmitted directly to the driver’s eyes, rather than the 2D windshield projections used in most display screens.

Mitigate human error

2 photos Example of technology

Enlarge

Although the technology has yet to be tested in a car, initial tests, based on data collected from a busy central London street, have shown that holographic images appear in the driver’s field of vision based on their actual position, create augmented reality.

This could be in particular useful in cases where objects such as traffic signs are obscured by large trees or trucks, for example, allowing the driver to “see through” visual obstacles.

“Heads-up displays are built into connected vehicles, typically projecting information such as speed or fuel levels directly onto the windshield in front of the driver, who must keep their eyes on the road,” says the lead author. Jana Skirnewskaja, Cambridge Engineering Department. . “However, we wanted to go further representation of real objects in the form of panoramic 3D projections“.

LiDAR is commonly used in agriculture, archeology and geography, but also being tested in autonomous vehicles for obstacle detection.

The latest BMW cars were created by artificial intelligence

Using LiDAR, the researchers scanned Malet Street, a busy street on the University College campus in central London. So the entire street was scanned using a technique called land laser scanning. Millions of pulses were sent from several places along rue Malet. The LiDAR data was then combined with the point cloud data, build a 3d model.

“This way we can join the scans and build a complete scene, which captures not only the trees, but also cars, trucks, people, signs and anything that can be seen on a typical city street. “, Explain the scientists. “Although the data we captured comes from a fixed platform, it is similar to the sensors that will be in the next generation of autonomous or semi-autonomous vehicles“.