AMETHYST: an enhanced detection system intelligently combining video detection and non-video detection systems

TLDR: The aim of the AMETHYST project is to encourage the development of a high performance perimeter intrusion detection system by combining Intelligent Scene Monitoring or Video Motion Detection technology with another detection system to produce a detection system with a high probability of detection and low false alarm rate.

Abstract: The aim of the AMETHYST project (AutoMatic Event auTHentication SYSTems) is to encourage the development of a high performance perimeter intrusion detection system by combining Intelligent Scene Monitoring (ISM) or Video Motion Detection (VMD) technology with another detection system The two systems would complement each other to produce a detection system with a high probability of detection and low false alarm rate The performance of Perimeter Intrusion Detection Systems (PIDS) is often poor at sites with long perimeters, with extreme weather conditions and requiring a high probability of detection Video based detection systems (ISM and VMD) are improving in sophistication and performance Despite this there are still limitations with video based defection Firstly, it may be several years before the video PIDS achieve the performance required for long perimeters Secondly, when there is no video, for example in fog, there is no detection There is potential for combining video detection with another sensor to reduce the disadvantages of video whilst retaining its advantages A non-video SIDS would be used to detect intrusions On alarm a sequence of CCTV images would be captured by a loop framestore system A Targeted Automatic Verification Aid (TAVA) would then be used to decide if there was suspicious activity in the alarm sequence Many false alarms have no visible cause, so a TAVA would filter these out The false alarm rate would be lower than with a normal VMD as a TAVA would need to assess only alarm sequences If there is no video or it is too foggy the TAVA would 'fail safe' by signalling the alarm from the non-video PIDS A TAVA could use more sophisticated processing than a VMD and still be cheaper, because it could target the processing PSDB is planning to collect alarm sequences from sites with a non-video PIDS and a loop framestore connected to the CCTV system These sequences will be used to prove the concept and evaluate the performance of a TAVA