Having problems with your account or logging in?
A lot of changes are happening in the community right now. Some may affect you. READ MORE HERE

How AI turns CCTVs into round-the-clock guards

Micro Focus Contributor
Micro Focus Contributor
0 0 1,683

Security operators tasked with monitoring multiple camera feeds have a very challenging job simply because they are humans. No wonder the United Kingdom’s Centre for the Protection of National Infrastructure (CPNI) recommends a 20 min1 shift for CCTV control room operators because of vigilance decrement, a common occurrence where attention decreases and oversight increases for tasks requiring intense and sustained attention. Threat scenarios vary so operators must also be able to react swiftly and appropriately. False alarms could be costly and missed detections could be deadly so control rooms are operating under tremendous pressure, which in turn increases the risk of errors.

How can Artificial Intelligence (AI) help? AI powered analytics can automate continuous monitoring and real-time detection of threats:

  • Physical area – Scene analytics can identify and classify unattended objects/vehicles and suspicious movement patterns. For example, an unattended clear glass bottle on a table in the middle of a room would be classified to have a risk profile, which is different from that of an unattended backpack at the corner next to a high traffic entrance.
  • Human – Face analytics can enable people counting for crowd traffic control and identity verification.  For example, a person on a watch list entering a public event can be identified and monitored.
  • Vehicle – License plates, makes and models can be read and referenced against a database. For example, suspicious vehicles w/mismatched plates can be identified.

Let’s look at one of the most common security breaches – tailgating. Basic courtesy of holding a door for a ‘fellow employee’ might lead to catastrophic consequences. With AI powered video analytics monitoring CCTV feeds from entrances, any individual whose image does not have a match in the authorized personnel database can automatically trigger an alarm. The unknown individual can be automatically enrolled for continuous tracking across the premise with other CCTV feeds to assist security intervention. While tailgating alone might not warrant a drastic response such as a lockdown, if there are other threats - unattended backpack at the corner of a cafeteria and a parked vehicle with a license plate registered to a terminated employee- detected within a short timeframe, it might lead to a different conclusion.

VIDSYS.jpg

If you are coming to ISC West, the largest US security event featuring the latest products, training, and networking in Las Vegas on April 10-12, find out more about how the Intelligent Global Security Operations Center (GSOC) can make a difference in your security operations. See how our AI-enabled Intelligent GSOC, a joint solution by Vidsys and Micro Focus IDOL, can turn each of your CCTVs into a 24X7X365 guard. Visit the Vidsys/Micro Focus Booth #34091 or better yet, register for your own appointment today.

 

1 - https://www.cpni.gov.uk/system/files/documents/aa/e6/human-factors-in-CCTV-control-rooms-a-best-practice-guide.pdf

 

About the Author
Joe has over 13 years of experience in technology marketing and is currently focused on the analytics solution portfolio. Prior to this role, he was responsible for product marketing of the enterprise application data management solution.
The opinions expressed above are the personal opinions of the authors, not of Micro Focus. By using this site, you accept the Terms of Use and Rules of Participation. Certain versions of content ("Material") accessible here may contain branding from Hewlett-Packard Company (now HP Inc.) and Hewlett Packard Enterprise Company. As of September 1, 2017, the Material is now offered by Micro Focus, a separately owned and operated company. Any reference to the HP and Hewlett Packard Enterprise/HPE marks is historical in nature, and the HP and Hewlett Packard Enterprise/HPE marks are the property of their respective owners.