|:: About Results||:: Publish/Update a Result||:: Technology Marketplace|
Periodic Report Summary - SAMURAI (Suspicious and abnormal behaviour monitoring using a network of cameras & sensors for situation awareness enhancement)
Quality validation date:2011-03-29
The aim of Samurai is to develop and integrate an innovative surveillance system for robust monitoring of both inside and surrounding areas of a critical public infrastructure site. Samurai has three significant novelties that make it distinctive from other recent and ongoing relevant activities both in the EU and elsewhere:
- Samurai is to employ networked heterogeneous sensors rather than CCTV cameras alone so that multiple complementary sources of information can be fused to create a visualisation of a more complete 'big picture' of a crowded public space.
- Existing systems focus on analysing recorded video using pre-defined hard rules, suffering from unacceptable false alarms. Samurai is to develop a real-time adaptive behaviour profiling and abnormality detection system for alarm event alert and prediction with much reduced false alarm.
- In addition to fix-positioned CCTV cameras, the Samurai system will also take command input from control room operators and mobile sensory input for patrolling security staff for a hybrid context-aware based abnormal behaviour recognition. This is in contrary to current video behaviour recognition systems that rely purely on information extracted from the video data - often too ambiguous to be effective.
Samurai will develop underpinning capabilities and tools for an innovative intelligent surveillance system to be used for the monitoring of both inside and surrounding areas of a critical public site (e.g. an airport concourse, an underground platform). The novelties of Samurai, which distinguish this project from other relevant activities both in the EU and elsewhere, are:
- Samurai is to employ networked heterogeneous sensors rather than isolated visual sensors (e.g. standalone CCTV cameras) so that multiple complementary sources of information are fused to visualise a more complete and 'big picture' of the area under surveillance.
- Samurai will advance intelligent video analytics beyond current post-incident analysis of a criminal/terrorist activity in recorded data. Samurai is to develop an online adaptive behaviour monitoring system for real-time abnormal behaviour detection and triggering of context-aware alerts in assisting the prevention of crime.
- Samurai will integrate fix-positioned CCTV video input with control room operator queries and mobile sensory input from patrolling staff for more effective man-in-the-loop decision-making. This is in contrast to current systems relying purely on processing sensory data.
- Two sets of initial datasets have been obtained from two sites. The major outcome of this so far is that a test site has been set up at the premises of Elsag Datamat S.p.A's.
- The first data collection exercise took place at Heathrow Airport, Terminal 3 in October 2009. There were 15 volunteers who demonstrated four scenes of abnormal or suspicious behaviour- including; abandoned luggage, theft of luggage, abandoned vehicle and unlawful group assembly. This data collection monitored by the ethics committee, has provided invaluable data to apply to the Samurai system for learning purposes.
- A functional design architecture diagram has been finalised by the project partners which will provide vital information on the input and output of various technical task modules of the system and the interaction between them.
- A prototype of the graphical user interface (GUI) has also been developed and has helped the specification and architecture design for the user interface component of the Samurai system.
- The core modules of the Samurai project have been produced.
A total of 21 conference papers (inc. ICCV'09, CVPR'09, BMVC'09, ECCV'10, CVPR'10, BMVC'10) and 6 journal submissions (inc. IJCV, PAMI), 2 keynote panel presentations have been generated by members of the Samurai consortium.
Source of support:CEC
|Programme||Project reference||Project title|
|FP7-SECURITY||217899||Suspicious and abnormal behaviour monitoring using a network of cameras & sensors for situation awareness enhancement|
Organization:QUEEN MARY AND WESTFIELD COLLEGE, UNIVERSITY OF LONDON
Position:Director of Visual Computation
Address: Department of Computer Science
Region: SOUTH EAST (UK) GREATER LONDON
Subject index:Information and communication technology applications , Information Processing, Information Systems, Security
Subject descriptors:Facilities Security, Communications networks, Image processing
Subject class:IT, Telecommunications
Record control number:45790