OmniPerception's News & Events

Cargo Security International: Brand Awareness

01 August 2009

Stewart Hefferman of OmniPerception argues that the video analytics technology currently being used to track exposure of commercial brands during major international sporting events has the potential to revolutionise cargo security.

Formula One racing is a prime illustration of the role that advertising plays in sport, with the major brands all vying for maximum audience exposure at such big events.

UK biometrics company OmniPerception has developed innovative logo tracking technology to allow sports marketing agencies to assess the brand exposure of big names such as Budweiser and Cinzano.

The Magellan™ technology is capable of detecting, analysing and recording the occurrence of logos, brands and other similarly distinctive images in television footage, video and other image based media.

The software detects and highlights each logo or other 'search target', adding a label to identify it for the human user and including a comprehensive set of associated information required by the customer (eg. position, size and degree of occlusion).

Magellan™ is capable of detecting a brand logo or object very accurately and very quickly, even when only a small part is visible or is partly occluded. It can also detect images that are somewhat blurred or presented in oblique, and can even cope with quite severely distorted presentations.

This includes the detection of insignias and slogans on sports clothing and vehicles as well as on the pitch, track-side billboards, race circuit bridges etc.

The way in which Magellan™ operates can be tuned very finely to fit the needs of an individual sponsor or brand owner, in terms of acceptable presence on screen, size, occlusion, position, and degree of blur or 'picture quality'.

The software collects all the necessary information in one pass, but the results can be re-tuned and re-presented as many times as necessary in response to specific customer enquiries about specific aspects of the footage -almost instantaneously, without the need to re-run any of the footage.

The technology has also been developed to be used in the law enforcement/security context under the name of Gama™. It has the potential to identify a suspect from his or her unique logo or feature of their clothing.

This is particularly useful as crime figures show that the majority of crime is committed by the same offenders.  Anecdotal evidence also suggests that offenders often wear the same distinctive clothing to commit repeat crimes almost as a 'badge of honour'.

It is this technology that has the potential to be used to improve security of cargo vehicles as they enter gated areas of ports and airports.

Gama™ is successful at finding, recognising and differentiating between cars, large trucks, pick-up trucks, taxis and police vehicles as well as aircraft and vehicle number plates presented at angles that can't be picked up by standard Automatic Number Plate Recognition (ANPR) technology.

It is also capable of finding relatively small wording or other distinguishing features on the sides or other parts of vehicles, pieces of equipment, cargo items and other objects.

In many cases, the distinguishing features may be characteristics of the objects themselves which could be a vehicle outline or a shape of baggage item and need not be separate markings.

Pictographs or search targets need not be pre-selected. They can also be taken from observed footage -the input from a closed circuit television (CCTV) camera, for example -and then used to scan footage from elsewhere, including historic, live or future footage.

A vehicle that arouses suspicion can be 'tagged' in this way and then monitored closely via the input from all site cameras.

Imagine if this technology were available to be used at ports and airports to identify vehicles as they approach security gates?

The software is capable of being 'trained' to identify, for example, a Sainsbury's truck as it drives up to the gates. This not only speeds up the time it takes for vehicles to enter and leave cargo areas, but it can also significantly improve security because only vehicles with pre-identified logos will be permitted into gated areas.

This could also be used for tracking security vehicles that may be carrying high value goods to cargo security areas.

A joint research programme into next generation face recognition and video analytics run by BAE Systems and OmniPerception is looking at the potential for such technology across a range of different security contexts.

The £1.5 million ($2.4 million) project is being funded by BAE Systems through its Investment in Innovation programme, which was set up in 2008 to encourage and support innovative small and medium sized enterprises (SMEs) in the development and delivery of new technology to improve security, in the UK and worldwide.

The face recognition and behavioural biometric work with OmniPerception is one of the programme's first projects.

Initial findings are expected later this year and it is hoped that the research will present border security personnel with cutting edge security solutions that could transform the way they use video analytic technology to improve security at the most vulnerable areas.