Ambarella, Smart Eye partner on next-gen AI-based driver monitoring
The platform is based on Ambarella’s low-power, high-performance CV22AQ CVflow computer vision processor. Smart Eye AI software running on the CV22AQ, say the companies, will make it possible for automotive OEMs and tier-ones to deploy a new generation of driver and in-cabin monitoring systems with advanced AI features, increasing safety and convenience for drivers and passengers.
“We are seeing significantly increased demand for both driver and in-cabin monitoring cameras,” says Fermi Wang, President and CEO of Ambarella. “Powered by CV22AQ, this joint platform will allow system designers to fully optimize Smart Eye’s innovative tracking technology in high-performance, low-power system designs.”
Martin Krantz, CEO of Smart Eye says, “We are very pleased to be working with Ambarella to enable advanced AI in the next generation of compact driver and in-cabin monitoring camera designs. With the Ambarella CV22AQ, Smart Eye is able to provide high-resolution, high-precision head pose, gaze, eyelid, and mouth tracking in 60 Hz paired with concurrent execution of our growing portfolio of AI-based interior sensing algorithms.”
Introduced last December, the CV22AQ supports both global shutter and rolling shutter CMOS sensors, both of which are required for in-cabin applications. The processor’s Image Signal Pipeline (ISP), with support for RGB-IR color filter arrays, enables high-accuracy detection and monitoring, even in low-light in-cabin environments.
The device’s High Dynamic Range (HDR) processing extracts maximum image detail in high-contrast scenes, further enhancing the computer vision capabilities of the chip and performance potential of Smart Eye algorithms. The CV22AQ CVflow architecture provides the computational power necessary for multi-camera monitoring system designs, running multiple AI algorithms on each video stream.
The CV22AQ includes a suite of advanced security features, including secure boot, TrustZone, and I/O virtualization to protect against hacking.
Related articles:
Automotive camera SoC combines AI with low power consumption
Image processing chip integrates DNN for AI applications
Why Carmakers Want to Monitor Drivers
AI recognizes personality through eye movements
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
