Ambarella will perform autonomous driving and parking demonstrations using its Embedded Vehicle Autonomy (EVA), a self-driving vehicle, on Las Vegas roads.

EVA builds upon 20 years of autonomous vehicle research and utilizes CVflow embedded processors to run AI-based computer vision algorithms. Its camera perception and 8-megapixel stereovision are implemented using Ambarella CV2 processors.

“With EVA our goal is to continue to push the limits of what’s considered achievable with computer vision-powered self-driving vehicles,” said Dr. Alberto Broggi, general manager of Ambarella, Italy. “CV2 provides the needed computational power with up to 20 times more AI performance compared to our previous generation CV1 chip.”

Key third-party demonstrations are as follows:

Mercedes-Benz will demonstrate its CV2-based Cargo Recognition and Organization System (CoROS): A camera assistant in the cargo space automatically recognizes registered parcels using barcodes and the symbols on the outside of the parcels. This process is done in fractions of a second, replacing manual, time-consuming scanning and sorting of each shipment.

Germany-based ADAS software supplier HELLA Aglaia will feature its latest suite of deep learning ADAS algorithms including multi-class object detection, detection of driving area limitations, depth estimation, and classification of traffic lights and traffic signs. Running on a single Ambarella CV22 CVflow SoC, this ADAS platform supports the development of single-box, forward-facing ADAS cameras.

Korea-based StradVision will demonstrate its suite of front ADAS and driver monitoring system (DMS) algorithms running on a single CV22. Connected to an 8-megapixel front-facing camera and an additional interior facing camera, this system will be installed and running in a vehicle.

Israel-based EyeSight’s driver monitoring solution (DMS) will be shown on a system with three cameras. In this demonstration, Ambarella’s CV25 simultaneously processes a monochrome driver-facing camera, and two RGB-IR in-cabin cameras (each with a different field of view).

Israel-based Brodmann 17’s ADAS solutions suite will showcase the company’s deep learning algorithms which include vehicle detection, distance estimation, and real-time forward collision warning running on a CV22 SoC.