Optical technology enhances conventional ADAS sensors

October 28, 2020 //By Christoph Hammerschmidt
Optical technology enhances conventional ADAS sensors
Lidar? Radar? Great, but not sufficient. Computational imaging company Light is entering the market of automotive sensor solutions with an optical-based perception platform that calculates distances and speeds from image data. According to the company, the system is able to see any 3D structures in the road from 10 centimeters to 1000 meters away. Which is about three times the distance of today’s best-in-class lidar systems.

With its development, an industry first, Light adds an interesting option to existing systems that augment the human driver, such as advanced emergency braking, as well as self-driving vehicles of the future that require sophisticated path planning. As Light Chief Product Officer Prashant Velagaleti puts it, it equips these cars and its sensor platforms with the near and long-range depth information required to make proactive, rather than reactive, decisions as their environment changes.

The technology, dubbed Clarity, allows vehicles to see more: It generates depth seamlessly fused with image detail across the entire camera field-of-view. This provides a vehicle with a dense, 3D view of its surroundings — at 30 times a second. The platform generates huge amounts of data – it generates up to 95 million data points every second, 20 times greater than any perception system currently available. The basis of these capabilities is a high performance signal processing technology - the company’s core know-how.


Comparison of optical image (left) and depth profile (right), computed by Light's Clarity platform.  

Clarity’s depth calculations are domain-independent. Thus, the system does not need to be trained to recognize the specific objects it may encounter on the road in order to derive 3D structure. A comprehensive understanding of the surrounding environment based on signal processing allows machines to operate proactively and robustly, making rides safer and smoother than systems relying on inferencing alone, Velagelati advertises.

The platform has been designed to accommodate a range of customer needs — functional, cost, and design related. It can be configured to optimize a number of driver-assist and autonomous systems.

“Automakers have invested billions of dollars and decades of research to make safe, reliable ADAS and self-driving cars a reality. But so far, even the best perception systems on the market miss objects and obstructions in the road — some as big as a semi-truck,” comments Light CEO Dave Grannan. “Any system that powers a


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.