How Self-Driving Cars Are Tweaked To See Better At Night

By Donna Bellevue , Mar 21, 2017 06:13 AM EDT

Scientists say they are on the cusp of giving self-driving cars the ability to drive better at night. Automated vehicles are making buzz recently as it allows people to do other things while driving. However, these cars have limitations, such as getting its optimal function only during sunny days.

Now, scientists are advancing the AI software used in these driverless cars so that they can read road signs in all sorts of weather and light conditions. The reason why driverless cars lack the reliability factor when it gets dark is due to its primary use of a camera. These visual sensors usually identify traffic signs, such as those indicating stops or speed limits, by detecting their distinctive shape, color, or other features.

However, rain, night time, and even trees can obscure these signs, making it difficult for driverless cars to confidently read them. To solve this problem inherent in self-driving cars, researchers at Sookmyung Women’s University and Yonsei University in Seoul found a way to work around the reflectiveness of road signs. Their strategy requires autonomous cars to continuously capture images of their surroundings, then feed it to a computer program that can quickly look through an image and decide whether it matches a known pattern, the Science Mag reported.

The technology can bring the vehicles one step closer to being safe enough for everyday people. Such is the goal of microchip manufacturer Intel, which has invested heavily in the driverless car race with the latest US$15 billion purchase of Israeli tech company Mobileye. Since most self-driving cars use a combination of sensing technologies to drive better on the road, Mobileye develops more sophisticated sensors and intelligence technology to operate many self-driving cars, The Conversation reported.

Its tech enables a car to “see” and understand the world through visual sensors, such as cameras, and range-to-object detection sensors, such as lasers and radar. Other interested investors include the deep learning tech company Nervana, microchip maker Movidius and automotive tech company Delphi. Scientists are also working on recognition for general road features like lane markers, though this has yet to undergo trials.

© 2020 ITECHPOST, All rights reserved. Do not reproduce without permission.
Real Time Analytics