First in a family of Ultra-HD computer vision processors based on Ambarella’s new CVflow architecture, the CV1 computer vision processor supports computer vision processing up to 4K or 8 MPixel resolution to enable object recognition and perception at extended distances. CVflow combines more than 20 years of research in environmental perception with advances in deep neural network processing to deliver stereo vision processing and deep learning perception algorithms to applications including advanced driver assistance systems, self-driving, electronic mirror and surround view systems, as well as video security cameras and fully autonomous drones.
CVflow architecture is fully programmable and enables convolutional neural network-based (CNN) classification to enable the detection of known classes like pedestrian, vehicles, motorcycles, while its stereo vision processing provides the ability to detect generic objects without training, allowing more robust decisions to be made in ADAS and autonomous vehicle applications, according to the company. The image signal processor features eight ARM Cortex A53 processor cores (up to 1 GHz), an RGB Bayer interface to popular image sensors, various image processing features, numerous peripheral interfaces, and tools for development including a CNN toolkit.
To Learn More:
Headquarters: Santa Clara, CA, USA
Product: CV1 computer vision processor
Key Features: CVflow computer vision framework, eight ARM Cortex A53 processor cores (up to 1 GHz)supports computer vision processing up to 4K or 8 MPixel.