Conferences and supporting programme
Deep Learning Requirements for Autonomous Vehicles
Deep-learning techniques for embedded vision are enabling cars to 'see' their surroundings and have become a critical component in the push toward fully autonomous vehicles. The early use of deep learning for object detection, e.g., pedestrian detection and collision avoidance, is evolving toward scene segmentation where every pixel of a high-resolution video stream must be identified. Embedded vision solutions will be a key enabler for making automobiles fully autonomous. Giving an automobile a set of eyes – in the form of multiple cameras and image sensors – is a first step, but it also will be critical for the automobile to interpret content from those images and react accordingly. To accomplish this, embedded vision processors must be hardware-optimized for performance while achieving low power and small area, have tools to program the hardware efficiently, and have algorithms to run on these processors.This presentation will discuss the current and next-generation requirements for ADAS vision applications, including the need for deep-learning accelerators. It will discuss how coming changes in deep learning will improve ADAS performance, and discuss how to evaluate the hardware and software tools needed to quickly deploy ADAS applications with high-definition resolutions.
--- Date: 28.02.2018 Time: 4:00 PM - 4:30 PM Location: Conference Counter NCC Ost