Home / ADAS / Xilinx to demonstrate solutions for ADAS and automated driving
Xilinx to demonstrate solutions for ADAS and automated driving
12 January, 2017
Xilinx, Inc. is to demonstrate solutions for ADAS and automated driving at CAR-ELE Japan. Demonstrations will including machine learning, computer vision and sensor fusion on Xilinx’s Zynq SoC and Zynq UltraScale MPSoC devices.
Deep Learning Using Convolutional Neural Networks (CNN) on Zynq UltraScale+ MPSoC
Demonstration showcases the use of the automotive industry’s first 16nm Zynq UltraScale+ MPSoC as an embedded computing platform for pedestrian detection using deep learning.Convolutional neural network (CNN, or ConvNet) is a type of feed-forward artificial neural network in which the connectivity pattern between its neurons is inspired by the organization of the animal visual cortex
Camera based Driver Monitoring System – Presented by Fovio
Real-time machine learning-based demonstration for head and eyelid tracking, combined with precision gaze direction measurement that allows reliable driver attention and driver state detection under a wide range of challenging real-world conditions.
Multi-Camera System using Ethernet Audio/Video Bridging – Presented by Regulus, NEC Communication Systems, Ltd. and Linear Technology
Sensor fusion demonstration implementing Ethernet-AVB in an automotive camera system. Using various camera modules based on the Zynq-7000 All Programmable SoC for image signal processing, object detection and distortion correction.
Advanced Camera/Display-based E-Mirror System – Presented by Toyota Tsusho Electronics Corporation
Demonstration of an e-mirror system based on the Zynq-7000 All Programmable SoC shows an innovative way to replace conventional rear-view mirrors in cars or other vehicles. The system displays how multiple camera inputs are combined with a set of displays
High-end Surround View System –
Sensor fusion demonstration of an advanced surround view virtual flying camera system enabling drivers to smoothly transition perspective of a three-dimensional view of the vehicle.