Stop false alarms
The Security Managers and Control Room operators who manage perimeter security systems in the external environment are constantly prompted by alarm events from perimeter security systems such as thermal cameras, visible cameras, barriers and sensors of various types.
Very often the alarm signals are due to environmental causes such as wind, rain, light reflections or the movement of small and medium-sized animals. When the number of false reports becomes high, it becomes difficult if not impossible for Control Room Operators to distinguish a real alarm event from the myriad of false events.
Compared to a few years ago, perimeter security systems have certainly made great strides forward, but the problem of managing false alarms seems to be very widespread, especially for those realities that need to protect very large areas, typical of the security sector. critical infrastructures and large industrial realities.
The rapid evolution of Artificial Intelligence systems applied to image analysis and the availability of relevant calculation capacity of the latest generation graphics processors open up interesting scenarios for the management of false alarms, unthinkable until recently.
The typical event management process in the Control Room foresees that in the event of an alarm, the operator visually checks the consistency of the alarm itself through the video stream of a surveillance camera; in practice, the operator tries to understand from the video whether or not a potential intruder is present in the area where an event was generated.
Through Artificial Intelligence systems it is possible to automate this process: when a perimeter system generates the intrusion event, an AI algorithm analyzes the video stream and verifies whether there is actually a target of interest in the scene. If the target is present the event is sent to the operator otherwise it is discarded.
This approach allows a reduction of up to 90% in the number of false alarms arriving in the Control Room, freeing operators from the burdensome verification task that can distract attention from real events that must be managed promptly.
Integration on plants
A false alarm reduction system based on Artificial Intelligence must be easily integrated into existing systems: on the one hand, it must be able to guarantee compatibility with all camera models, from the older analog cameras to the latest generation IP Multimegapixel ones, on the other hand, it must be able to communicate with the main Video Management systems on the market in order to forward the alarm events once they have been validated.
Turn cameras into Radar and reduce false alarms
IntelliDetect is a software module developed by Crisma Security, the only one on the market capable of equipping any fixed or PTZ camera with features typical of Radar systems.
Thanks to the use of advanced Computer Vision techniques, it allows to detect and classify targets with extreme precision, reducing the number of false alarms by over 90% compared to traditional video analysis systems.
Simplify the work of man
An advanced system for the reduction of false alarms must also be equipped with other useful functions to facilitate the work of the control room operators, such as the possibility of extrapolating the GPS coordinates of the detected targets from the video stream. Through this ability to georeference the target, security operators can follow the movements of intruders in real time on a map such as Google Maps, over areas extended for several kilometers and knowing the precise position of the patrons is very useful for quickly understanding the exact position. of intrusion and the path taken.
Thanks to this functionality, it is as if each camera were equipped with the typical functions of radar systems, with the ability to distinguish the types of targets and to detect their position in real time in GPS coordinates on the map.
Usage must also be smart
Another useful feature for filtering out false alarms is the intelligent use of PTZ cameras. These cameras in most cases are not exploited adequately because they are used passively through preset tours or controlled by an operator. An advanced system on the occurrence of an alarm is able to automatically control the PTZ camera to follow the movements of the intruder with the possibility of using the AI to validate or not the presence of the target.
In this way the camera from a passive instrument becomes an active scanning system with the ability to detect intrusions and to automatically follow the targets, while providing the positioning information on the map.
AI for outdoor perimeter protection
The simplicity of implementing the false alarm filter system with Artificial Intelligence is fundamental and the architectural impact must be minimal and must not require major changes to the existing security infrastructures. Interoperability between the components must be ensured.
The false alarm filter system based on Artificial Intelligence is an extremely valid tool to increase the effectiveness of outdoor perimeter protection systems, a fundamental module that cannot be missing in a new generation Control Room.