Ambarella introduces new high performance camera chips for autonomous cars at CES 2020

Ambarella, an AI vision silicon company, today announced the CV22FS and CV2FS automotive camera system on chips (SoCs) with ‘CVflow’ AI processing and ASIL B compliance to enable safety-critical applications. Both chips target forward-facing monocular and stereovision ADAS cameras, as well as computer vision ECUs for L2+ and higher levels of autonomy.

Featuring extremely low power consumption, Ambarella claims that the CV22FS and CV2FS make it possible for tier-1s and OEMs to surpass New Car Assessment Program (NCAP) performance requirements within the power consumption constraints of single-box, windshield-mounted forward ADAS cameras. Other potential applications for the processors include electronic mirrors with blind-spot detection (BSD), interior driver and cabin monitoring cameras, and around view monitors (AVM) with parking assist.

The two new SoCs are the latest additions to Ambarella’s CVflow SoC family that offers automotive OEMs, tier-1s, and software development partners an open platform for differentiated, high-performance automotive systems.

ZF, a global technology tier-1 and supplier of systems for passenger cars and commercial vehicles, is working with Ambarella on viewing and sensing systems. Aaron Jefferson, vice president of ADAS product planning at ZF said, “ZF is pleased to be working with Ambarella on the next generation of intelligent viewing platforms for Surround View Visualization, Driver Monitoring stand-alone vision processing, and e-mirror solutions for both the passenger car and commercial vehicle markets. The CVflow SoCs’ combination of high-quality imaging and advanced AI processing enables ZF to offer a wide range of viewing and interior sensing applications.”

Hella Aglaia, a leading global developer of intelligent visual perception software, has worked with Ambarella’s CVflow processors over the past year. Kay Talmi, managing director at Hella Aglaia said, “We chose Ambarella’s CVflow SoCs due to their ability to deliver extremely high computer vision processing performance with very low power consumption. With the introduction of the CV22FS and CV2FS ASIL SoCs, Ambarella now delivers the functional safety features required by automotive OEMs for the mass production of safety-critical systems.”

Fermi Wang, president and CEO of Ambarella said, “Ambarella’s CVFlow architecture delivers an unparalleled combination of AI performance and power efficiency. We are pleased to introduce these ASIL-compliant CVflow SoCs, delivering on our promises to our partners and customers and further demonstrating our commitment to the automotive market.”

Ambarella explains that the CV22FS and CV2FS’s CVflow architecture provides computer vision processing in 8-megapixel or higher resolution at 30 frames per second for object recognition over long distances and with high accuracy. The SoCs each include a dense optical flow accelerator for simultaneous localisation and mapping (SLAM), as well as distance and depth estimation. Multi-channel high-speed sensor input and Ambarella’s image signal processing (ISP) pipeline provide the necessary camera input support, reportedly even in challenging lighting conditions. CV2FS also enables advanced stereovision applications by adding a dense disparity engine.

CV22FS and CV2FS are scheduled to sample to Ambarella customers in the first half of 2020.

CV22FS and CV2FS SoC key features:

- CVflow architecture with DNN support

- Quad-core 1-GHz Arm Cortex-A53 with NEON DSP extensions and FPU

- Safety island with dual-core lock step (DCLS) Arm R52 targeting ASIL-C

- Dense optical flow engine

- Dense stereo disparity engine (CV2FS only)

- ASIL B functional safety level

- High speed SLVS/MIPI CSI-2/LVCMOS interfaces

- Multi-channel ISP with up to 480-Megapixel/s input pixel rate

- Native support for RGGB, RCCB, RCCC, RGB-IR, and monochrome sensor formats

- Multi-exposure high dynamic range (HDR) processing and LED flicker mitigation

- Real-time hardware-accelerated fish-eye dewarping and lens distortion correction (LDC)

- 4-megapixel AVC encoding for video logging and wireless video streaming

- Rich set of interfaces includes CAN FD, Gigabit Ethernet, USB 2.0 host and device, dual SD card controllers with SDXC support, MIPI DSI/CSI-2 4-lane output

- Advanced security features, including OTP for secure boot, TrustZone, and IO virtualization

- AEC-Q100 grade 2 (-40C to +125C (T_J) operating temperature)

- 10 nm process technology