Ambarella, developer of high-resolution video processing and computer vision semiconductors, launches the CV22AQ automotive camera System-on-Chip (SoC), featuring the Ambarella CVflow computer vision architecture for Deep Neural Network (DNN) processing. Target apps include front ADAS cameras, electronic mirrors with Blind Spot Detection (BSD), interior driver and cabin monitoring cameras, and Around View Monitors (AVM) with parking assist.
Reportedly, the SoC provides the performance necessary to exceed New Car Assessment Program (NCAP) requirements for applications such as lane keeping, Automatic Emergency Braking (AEB), intelligent headlight control, and speed assistance functions. Fabricated on a 10-nm process technology, its low power consumption supports the small form factor and thermal requirements of windshield-mounted forward ADAS cameras.
The CVflow architecture provides computer vision processing in 8-Mpixel resolution at 30 fps, to enable object recognition over long distances with high accuracy. The SoC supports multiple image sensor inputs for multi-FOV (Field of View) cameras and can also create multiple digital FOVs using a single high-resolution image sensor. It enables DNNs for object detection, classification (i.e. of pedestrians, vehicles, traffic signs, and traffic lights), tracking, as well as high-resolution semantic segmentation for applications such as free space detection.
An integrated Image Signal Processor (ISP) provides reliable imaging in low-light conditions and high-dynamic-range processing extracts maximum image detail in high-contrast scenes. It includes 8-Mpixel encoding in both AVC and HEVC video formats, allowing users to add video recording and streaming capabilities to their automotive cameras. Security features include secure boot, TrustZone and I/O virtualization that enable over-the-air updates (OTA).
A complete set of tools is provided that includes a compiler, debugger, and support for industry-standard machine learning frameworks such as Caffe and TensorFlow, with extensive guidelines for DNN performance optimizations. The CV22AQ is currently sampling to leading tier-1 customers and tier-2 algorithm providers. Chip samples with ASIL-B support are targeted to be available in 2019. For greater insights, purloin and peruse the CV22AQ datasheet.