Maths to turn people's media into national news
11 Oct 2012
Technology will put the power to make news into the hands of ordinary people and revolutionise the way the vast reservoir of the public's digital content is handled thanks to new research, funded by the Engineering and Physical Sciences Research Council (EPSRC).
Automatically amalgamated, time sequenced packages of digital images and audio from individuals at major news events, such as the 7/7 bombings or the Olympic Games, could soon be transforming the content of news broadcasts.
'Multisource audio-visual production from user-generated content' is led by Professor Andrea Cavallaro who is based at the School of Electronic Engineering & Computer Science, Queen Mary University of London and starts in October 2012.
It will investigate ways of taking digital content from multiple sources, such as people's mobile phones or cameras. It will aim to automatically filter and mix it to provide packages for editors to include in news broadcasts from breaking events such as; protests, disaster scenes, sports events and music concerts.
The research's focus is on being able to use artificial intelligence and complex mathematical calculations to combine crowd-generated footage of an event and generate professional standard reportage from it.
These algorithms will be used to identify edits and links between events, such as timings and viewpoints. This will also be relevant to security, as a means of wading through a vast quantity of CCTV footage.