ON Semi demos integrated in-cabin monitoring system 

September 17, 2019 //By Christoph Hammerschmidt
ON Semi demos integrated in-cabin monitoring system 
ON Semiconductor is featuring an in-cabin monitoring system inclusive of driver monitoring and occupancy monitoring functions at the AutoSens Conference in Brussels, Belgium. The multi-camera system features ON Semi’s RGB-IR image sensor, Ambarella’s advanced RGB-IR video processing SoC, and Eyeris’ in-vehicle scene understanding AI software.

The demonstration includes multiple sensor types from ON Semiconductor - the 1 Megapixel (MP) Global Shutter  AR0144AT image sensor  and three 2.3 MP RGB-IR image sensors. This multi-camera system utilizes Ambarella’s CV2AQ System-on-Chip (SoC) that processes real-time high-quality RGB-IR video and integrates Eyeris’ AI software performing complex body and facial analytics, passenger activity monitoring, and object detection. 

Driver and occupant monitoring applications require the ability to capture images in variable lighting from direct sunlight to pitch black conditions. With outstanding NIR response, the RGB-IR CMOS image sensor technology provides full HD 1080p output using a 3.0 µm backside illuminated (BSI) and three-exposure HDR. Sensitive to both RGB and IR light, the sensors are able to capture color images in daylight and monochrome IR images with NIR illumination. 

Netx-generation safety features currently under development in the automotive industry include child presence detection, said Ross Jatou, VP and General Manager for ON Semi’s Automotive Sensing Division. To optimize performance and to cut time-to-market for such in-cabin systems, a strong collaboration between sensor, processor and software companies is imperative, he added.

Ambarella is contributing its CV2AQ SoC that combines the company’s proprietary CVflow DNN engine and high-performance image processing. On this SoC runs Eyeris’ vision-based DNN for in-vehicle scene understanding applications.

More information: ON

Related articles:

Camera chip uses AI for monitoring applications

Automotive camera SoC handles Deep Neural Networks at low power consumption


Vous êtes certain ?

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

Vous allez être rediriger vers Google.