Skip to the content

Follow us @UKAuthority

Met Police takes part in video analytics development

25/10/16

Forensic image team provides input into design of system using supercomputer technology to speed up search for evidence

The Central Forensic Image Team of the Metropolitan Police has been involved in testing a technology to speed up the processing of data and video footage in criminal investigations.

SeeQuestor screen - shows video from two sources on mapIt has been one of a number of police forces from around the world using the SeeQuestor system, which includes integrated software and hardware, on data from previous cases in pre-launch tests.

The key element of the system is the processing capacity of a supercomputer – up to 60 teraflops, which is a trillion floating point operations per second.  It is combined with intelligent software and graphics processors to analyse video footage, with the company behind the development – also named SeeQuestor – saying it makes it possible to index 24 hours of video footage in as little as 15 minutes.

The company said the Met Police and British Transport Police have been among those providing input to the design and running test cases.

Detective Chief Inspector Mick Neville, head of the Met’s Central Forensic Image Team, suggested the system could make a significant difference in searching through heavy volumes of video footage.

"The current technology is quite simply not up to scratch,” he said. “When the police see enormous amounts of video, that has to be viewed manually and normally it takes one person one hour to review - it's almost an impossibility to do that much.

“A system that will automate this and quickly scan the footage, it may give us the links and major leads that we can focus on. Anything that makes man and machine work together in perfect harmony to get us to identify more criminals and find more victims would be a wonderful tool for the police."

The SeeQuestor system makes it possible for forensic teams to import thousands of hours of video, converted to MPEG4 H.264 format, and filter out unnecessary footage so that most likely to provide evidence can be analysed. It uses features including person recognition, face detection, attribute search, geo location information and a motion detection filter.

A 2015 College of Policing analysis of the demand on police services pointed to a risk that, as police are forced to work on tightening resources, their time will be taken up with reactive rather than preventative work, such as patrolling and intelligence gathering.

“This type of activity which helps the police to understand what is causing high volume offending or problems in hotspots, and come up with specific solutions – often in partnership with others – allows the police to drive down crime,” the report said.

Image from SeeQuestor

Register: Library & Alerts

Keep informed - Get the latest news about the use of technology, digital & data for the public good in your inbox from UKAuthority.