SANTA CLARA, Calif.--(BUSINESS WIRE)--Ambarella, Inc. (NASDAQ: AMBA) a leading developer of low-power, HD and Ultra HD video processing semiconductors, today announced CV1, the first in a family of Ultra-HD computer vision processors based on Ambarella’s new CVflow architecture. CVflow combines over 20 years of pioneering research in environmental perception with advances in DNN (Deep Neural Network) processing to deliver stereovision processing and deep learning perception algorithms to a variety of automotive applications, including ADAS, self-driving, electronic mirror and surround view systems, as well as video security cameras and fully autonomous drones.
CV1 supports computer vision processing up to 4K or 8-Megapixel resolution to enable object recognition and perception at extended distances. The CVflow architecture is both fully-programmable and highly-efficient, providing significant computer vision performance with very low power consumption. Its stereovision processing provides the ability to detect generic objects without training, allowing more robust decisions to be made in ADAS and autonomous vehicle applications. The advanced ISP (Image Signal Processor) includes HDR (High Dynamic Range) processing to deliver high quality images, even in low light and high-contrast environments.
“We are delighted to introduce CV1, the first in a new family of 4K computer vision processors based on our CVflow architecture,” said Fermi Wang, CEO of Ambarella. “CV1 combines Ambarella’s traditional strength in high-resolution imaging for human vision with stereo and neural network processing for advanced computer vision. It will provide customers with a highly programmable and high-performance platform to develop the next generation of intelligent vehicles, drones and IP security cameras.”
A complete set of software development tools is provided for CV1, including compiler, debugger and support for high-level decision and low-level perception layers. Customers can easily port their own neural networks to CV1 using industry-standard training tools including Caffe™ and TensorFlow™, together with extensive guidelines for CNN (Convolutional Neural Network) performance optimizations.
During the CES 2018 show, Ambarella will demonstrate its “EVA” (Embedded Vehicle Autonomy) vehicle, featuring multiple CV1-based SuperCam™ cameras to provide 360-degree short- and long-range perception and precise self-location. SuperCam’s 4K stereovision processing provides a perception range of over 150 meters for stereo obstacle detection and over 180 meters for monocular classification. Its features include automatic calibration, stereo generic obstacle detection, terrain modeling, traffic light detection, 3D free space detection, lane detection, and CNN classification for vehicle, pedestrian, and bicycle/motorcycle.
Also during the show, Ambarella will demonstrate its fully-autonomous CV1-based SuperDrone™ platform. SuperDrone features include path planning, target tracking, obstacle avoidance, multi-point navigation, 3D free space detection, enhanced safety shield and GPS-denied precise visual localization.
The URL for this news release is www.ambarella.com/about/news-events.html
About Ambarella
Ambarella, Inc. (NASDAQ: AMBA), is a leading developer of low-power, high-definition (HD) and Ultra HD video compression, image processing, and computer vision solutions. The company’s products are used in a variety of IP security, sports, wearable, drone, and automotive video cameras. Ambarella’s solutions leverage over 20 years of pioneering research in computer vision to enable future generations of intelligent cameras, Advanced Driver Assistance Systems, and autonomous vehicles. For more information about Ambarella, please visit www.ambarella.com.