Onsemi’s image sensor Hyperlux available on the NVIDIA DRIVE autonomous drive solution
Date: 06/10/2023
Onsemi has announced that its Hyperlux Image Sensor family drivers are now available on the NVIDIA DRIVE platform, an autonomous driving solutions for vehicles. This safety enhancing support allows automated driving systems to fully utilize the sensor’s benefits allowing capturing of more details across any lighting condition.
Hyperlux image sensors help capture detailed images and avoid blind spots without the need to change exposure settings. This provides the highest quality data for the NVIDIA DRIVE platform to process and make better, informed decisions quickly. These sensors are designed to consume low power and by leveraging efficient architecture of the NVIDIA platform is touted as lowest power option available for autonomous vehicle (AV) operation.
NVIDIA DRIVE is an open, scalable AI platform that consists of hardware, software and firmware that work together to enable the production of automated and self-driving vehicles.
“Uncompromising image quality is imperative for autonomous vehicles and there is an expectation for the vehicles to perform better than human drivers,” said Chris Adams, vice president, Automotive Sensing Division at onsemi. “By offering Hyperlux as part of the NVIDIA DRIVE platform automakers get a system that can see problems before drivers do and make better decisions to avoid them, which is a critical step to achieving fully autonomous driving.”
The Hyperlux Image Sensors are the only sensors available today that offer 150 dB high dynamic range (HDR) that can meet and exceed those expectations. For example, with Hyperlux Image Sensors, an AV can distinguish between a yellow and red stoplight at a distance, even when facing a setting sun in a situation where human eyes would likely be blinded. Even in very low light, performance exceeds requirements with super exposure pixel technology, capturing people, animals and objects that may be difficult to see while driving.
The Hyperlux sensors give the NVIDIA DRIVE platform the information needed to make more accurate decisions because they nearly eliminate dropped frames that could contain critical details or moments when other sensors need to change exposure mode for a clear picture. Without that delay, the system can see and make decisions on anything in view, including objects the human eye couldn’t see.
“Building public confidence toward self-driving means being able to offer the assurance that these supercomputers-on-wheels can get you where you need to go, safely,” said Glenn Schuster, senior director of sensor ecosystems at NVIDIA. “With Hyperlux image sensors now part of our ecosystem, we can continue to provide our OEM and tier 1 customers with the best choices for their unique needs—ensuring the highest levels of system performance, functional safety, and cybersecurity.”
To ensure safety, image sensors need to be stable and perform, no matter what condition they are in. At extreme temperatures, image quality degrades, which makes the overall system less effective for perception tasks such as object detection and classification. The Hyperlux family avoids degradation with its ability to work at spec performance and deliver best-in-class image quality for both viewing and sensing applications across the entire automotive temperature range, from -40 C to 125 C. Not only does the Hyperlux Family have the ability to achieve a clear image, even in hot conditions, it can also capture fast-moving objects, car headlights, and flickering lights for higher system safety.
For more information on our Hyperlux family, visit:
https://www.onsemi.com/solutions/technology/hyperlux
Source: Onsemi
