You are here

Cloud Large Scale Video Analysis

Column 1
Funding Programme or Company Name: 
H2020 - ICT - 2015
Funding Body: 
European Union - Horizon 2020 (Societal Challenges)
It can be argued that CMOS cameras are the most ubiquitous and utilised sensor in our daily lives, currently present in our phones, tablets, laptops, watches and, increasingly, in our cars. They capture and supply an enormous volume and variety of data at ever increasing velocity. In 2014 the market for CMOS image sensors was valued at $8.4 Billion (USD). Asian manufacturers are dominant in the CMOS image sensor sector (e.g. Sony 39.5%, Samsung 15.7%) driven primarily by demand in smartphones and tablets, however, 29.2M units were sold to the automotive industry alone. It is estimated that a car in 2020 will contain a minimum of 10 cameras driving global demand to 102M units in that year, with growth to continue to 2030. The Cloud-LSVA project presents a research plan to advance technology and performance in the key automotive industry by employing Semi-Automated Video Annotation, Scene Recognition, Object Recognition and Deep Learning, in conjunction with vehicle sensor data, on a petabyte scale leveraging the elasticity of computing resources offered by Cloud Computing. The complexity of data produced by automotive sensors presents a significant research challenge that, if addressed, will provide quantifiable impact on European society and industries, such as automotive safety and infotainment, where the EU currently maintains a lead over North American and Asian competitors. Cloud-LSVA will focus on applications in the Advanced Driver Assistance Systems (ADAS) and Digital Cartography domains. Real consumer demand for the next generation of ADAS technologies exists and is growing2 and both domains are key underpinning elements of the Semi-Autonomous and Autonomous vehicle initiatives. Self-driving cars are expected to become a reality on our roads in 20203. However, even if regulatory and technological obstacles prevent autonomous vehicles, advances in Advanced Driver Assistance Systems (current) and Semi-Autonomous driving (beyond 2017) will be a reality.
Insight Contact: 
Application Domain: 
Research Group: 
Associated Theme for Application Domain: 
The Discovery Economy-The Analytical Society
Column 3
Funding Body Logo: 
Involved Institution: 
Dublin City University (DCU)
Committed Cost Share (in kind):