Neural Video Processing and Streaming for Real-time Traffic Monitoring

Project description

AI for real-time traffic monitoring

Rapid urbanisation and the permanent increase in vehicle numbers raised concerns about road safety. As a result, real-time traffic monitoring systems have been installed to assist operators in traffic control and emergency situations. The EU-funded VISIONS project will develop a real-time traffic monitoring system with high-quality video transmission in smart cities based on AI methods in video processing and video streaming. The characteristics of human visual systems will be denoted on video quality allocation to restrict the necessary range for video transmission. An advanced method based on deep neural networks will be deployed to permit video rendering and streaming at lower resolutions, and a novel bitrate adaptation system based on reinforcement learning will be planned to guarantee quality-of-experience.

Fields of science

• natural sciences › computer and information sciences › software › software applications › virtual reality
• engineering and technology › civil engineering › urban engineering › smart cities
• natural sciences › computer and information sciences › artificial intelligence › machine learning › reinforcement learning
• natural sciences › computer and information sciences › artificial intelligence › computational intelligence

Programme(s)

• H2020-EU.1.3.2. - Nurturing excellence by means of cross-border and cross-sector mobility

Topic(s)

• MSCA-IF-2019 - Individual Fellowships

Call for proposal

H2020-MSCA-IF-2019
See other projects for this call

Funding Scheme

MSCA-IF-EF-ST - Standard EF

Coordinator

THE UNIVERSITY OF EXETER

Address

The Queen's Drive Northcote House
EX4 4QJ Exeter
United Kingdom

Activity type

Higher or Secondary Education Establishments

EU contribution

€ 224 933,76