Platform to leverage Ambarella’s high-performance, low-power CVflow® computer vision architecture and Baolong’s automotive visual perception algorithms
Ambarella, (NAMBA), a developer of high-resolution video processing and computer vision semiconductors, and Shanghai Baolong Automotive Technology, a supplier of intelligent automotive sensors, announced a joint project to develop a high-performance driver monitoring system (DMS) platform with advanced artificial intelligence (AI) capabilities for assessing driver fatigue. The DMS platform will be based on Ambarella’s CV22AQ CVflow® computer vision chip and Baolong’s visual perception software.
“Our partnership with Ambarella to develop an advanced AI-based DMS solution will help enable the automotive industry’s shift toward including driver monitoring in production vehicles,” said Li Wei, director of Baolong’s electronics unit. “Ambarella’s CV22AQ CVflow computer vision processor is ideal for our visual perception algorithms: it provides the high performance and low-power consumption required for compact DMS camera designs.”
“We are pleased to be collaborating with Baolong to enable next-generation automotive cameras for improved driver safety,” said Ambarella CEO Fermi Wang. “With this joint platform, our customers gain a high-resolution, high-accuracy DMS solution with advanced AI features.”
Baolong’s DMS software captures the driver’s facial information, including characteristics of the eyes, head, and mouth from an image sensor. Ambarella’s computer vision SoC then performs image processing and AI-based analysis to determine the driver’s level of fatigue in real time.
Ambarella’s CV22AQ chip offers support for both global shutter and rolling shutter CMOS sensors, a requirement for applications deployed inside a vehicle’s cabin. The CV22AQ includes a powerful ISP, native support for RGB-IR color filter arrays, and advanced high dynamic range (HDR) processing, which results in exceptional image quality in low-light and high-contrast environments. CV22AQ’s CVflow architecture delivers the computational power required for multi-camera DMS solutions, while running multiple AI algorithms on each video stream. CV22AQ includes a suite of advanced security features to protect against hacking, including secure boot, TrustZone™, and I/O virtualization.