Researchers Claim Camera Could Aid AV Vision

Academics have created a camera they say could improve autonomous vehicles’ hazard detection abilities in challenging weather conditions.

The University of Illinois researchers say it can do this by a combination of “polarization” and atypically high “dynamic range”. Polarization is the process by which a camera is able to differentiate objects from one another according to their varying light levels, and dynamic range is the difference between “the brightest and darkest areas a camera can capture simultaneously”. The researchers claim these qualities of their camera could enable an AV to see better when making sudden transitions between settings whose light levels differ drastically and in very foggy or hazy driving conditions.

Lead researcher Viktor Gruev said: “In a recent crash involving a self-driving car, the car failed to detect a semi-truck because its color and light intensity blended with that of the sky … our camera can solve this problem because its high dynamic range makes it easier to detect objects that are similar to the background”. His colleague Tyler Davis added: “We used the camera under different driving lighting conditions such as tunnels or foggy conditions … [it] handled these challenging imaging conditions without any problems”.

The team claim it “would enable cars to detect hazards, other cars and people three times farther away than color cameras” currently deployed in cars and “could be mass-produced” at a cost of $10.

 


Leave a comment

Your email address will not be published. Required fields are marked *