Adabts en
Uploaded by
XiryumAdabts en
Uploaded by
XiryumEnterprise & Industry
ADABTS Automatic Detection of Abnormal Behaviour
and Threats in crowded Spaces
Camera 01
Camera 02
Project objectives
ADABTS aims to facilitate the protection of EU citizens, property and infrastructure against threats of terrorism, crime and riots by the automatic detection of abnormal human behaviour. ADABTS aims to develop models for abnormal and threat behaviours and algorithms for automatic detection of such behaviours as well as deviations from normal behaviour in surveillance data. ADABTS aims to develop a real-time evaluation platform based on commercially available hardware, in order to enable high-performance low-cost surveillance systems.
advanced methods for sensor data analysis are needed. These methods should extract sensor data features that can be coupled to the dened behaviour primitives, and thus detect the presence of the (potentially) threatening behaviour and to detect behaviour that is not considered normal. ADABTS will develop new and adapt existing sensor processing methods and algorithms for detecting and tracking people in complex environments, involving groups of people or crowds. Extracted sensor data features (e.g. tracks, voice pitches, body articulations) need to be related to the behaviour primitives, and, moreover, to be dynamic and adapt to the context. ADABTS will adapt the above algorithms to run on commercially available low-cost hardware architectures consisting of multi-core CPUs combined with several multi-stream GPUs (Graphical Processing Units). Such hardware, in rapid development driven by the game industry, represents a huge potential for highperformance surveillance systems. ADABTS will communicate results to the various kinds of identied actors: Security stakeholders like European and national authorities, police organisations or event organizers; Security system operators and security service companies; Security system integrators; Technology developers; the Research communities for psychology, human factors, and signal processing communities. ADABTS will involve all these actors, either as principal contractors, as subcontractors, or in an associated stakeholder group.
Expected results
The main impact of the ADABTS project is expected to be on the technological level, with advancements in three directions: Understanding of the user needs for automatic detection of abnormal behaviour in crowds and new denitions of and methods for describing such behaviour. Methods and algorithms for abnormal behaviour detection based on video and acoustic sensors. Real time optimization for commercially available low-cost hardware, including an online demonstration of capabilities at a football stadium.
Description of the work
ADABTS will gather experts in human factors, signal processing, computer vision, and surveillance technology. In a rst stage, focus will be on human factors in order to dene and model behaviours. Then, the focus will be shifted towards automatic analysis of surveillance data (video and audio). Finally, a demonstration system will be implemented. ADABTS will create models of behaviour that can be used to describe behaviours to be detected and how they can be observed. Such models will enable the prediction of the evolution of behaviour, so that potentially threatening behaviour can be detected as it unfolds, thus enabling pro-active surveillance. In order to detect behaviour dened by these models,
Overview
INFORMATION
Acronym : ADABTS Grant Agreement N : 218197 Total Cost : 4,478,990 EU Contribution : 3,229,034 Starting Date : 01/06/2009 (expected) Duration : 48 months Coordinator : TOTALFORSVARETS FORSKNINGSINSTITUT (FOI) Division of Information Systems Postal Box: 1165 Sweden - SE-58111 Linkping Contact : Jrgen Ahlberg Tel : +4613378068 Mobile: +46706757384 Fax : +4613378287 e-mail : adabts_coordinator@foi.se
PARTNERS
NAME COUNTRY Totalforsvarets Forskningsinstitut (FOI) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Sweden BAE Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . United Kingdom Detec A/S . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Norway Home Oce Scientic Development Branch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . United Kingdom Institute of Psychology Ministry of the Interior . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Bulgaria SINTEF . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Norway TNO . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . The Netherlands University of Amsterdam . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . The Netherlands
