A technological surveillance solution designed to keep law abiding citizens safe while at the same time respecting their privacy has been developed by EU-funded researchers.
The team of scientists behind the MOSAIC project, which recently announced its key outcomes, are now considering further research and commercial collaborations based on their achievements.
The results of the project come at a time when there is a growing public debate over the extent to which surveillance is justified, and how the right balance between civil protection and personal privacy can be achieved.
By developing smarter surveillance technologies capable of automated detection, recognition and mapping, the MOSAIC project – which was completed at the end of July 2014 – could help law enforcement authorities reconcile these two important demands.
Surveillance is an increasingly common – and sometimes controversial – activity, designed fundamentally to protect public and property. The rapid increase in information gathered by surveillance cameras however has led to spiralling costs in terms of storage filtering and data checking, and has also led to concerns that innocent citizens are routinely being tracked.
The project sought to streamline surveillance through the development of a number of decision-support technologies. These technological innovations are based on video analytics, using data methods that search tags and fuse data from both multimedia sources and information databases.
The distributed intelligence within the platform enables decision support for automated detection, recognition, geo-location and mapping, including intelligent decision support at various levels to enhance situation awareness, surveillance targeting and camera handover. The technology also enables cameras to filter out unimportant events, meaning that surveillance is more focused and targeted.
This means that the privacy of citizens is safeguarded, while law enforcement authorities are able to reduce the number of man hours spent sorting through raw data.
The project team worked closely with law enforcement agencies to ensure that their tools were practical and applicable. An analysis of end-user requirements from police and CCTV operators was carried out, which helped in the design of the overall MOSAIC architecture.
Prototype MOSAIC components for data representation, text and data mining, social and criminal network analysis and decision support were then successfully developed. The design of a new smart camera system capable of being integrated into the MOSAIC platform was also completed. The final integration of all these MOSAIC components achieved an overall satisfaction level of 79.88 % in final trials with end users.
The MOSAIC project will have important implications that extend beyond law enforcement. Analytical innovations could also be relevant to other areas such as the analysis of shopping behaviour, social networks, speech analytics or data mining.
The team is now looking at possibilities of developing the technology further, along with the possible commercialisation of the complete platform. Further development and the commercialisation of individual platform components are also being investigated.
For further information please visit www.mosaic-fp7.eu.
