Page 21 - Campus Security & Life Safety, July/August 2023

"So, the hard truth is, for the majority of video surveillance systems in schools, nobody is watching the video feeds in real time. No one is going to see an assailant coming."
Analytics and AI Make a Powerful First Line of Defense
AI-based cameras can detect people and vehicles while also capturing the unique identifying characteristics of both. This means it’s possible to search for a student with a red shirt, wearing glasses and carrying a backpack. It’s revolutionary since such a search can be conducted in seconds compared to a manual search by a person. This ability of AI to detect known objects has made analytics (which report the behavior of those objects) incredibly powerful as a first line of defense. Analytics let us know if an actual person is loitering or entering a restricted area after hours. For example, if our red-shirted student wearing glasses is in the chemistry supply room after hours, we might want to notify security. This ability to notify while events are occurring is a crucial advancement in campus-based video surveillance that no school should be without.
When adopting a more proactive security stance, such automated event notification is vital for early detection and warnings. With some VMS solutions you can isolate an intruder, register their face, and set alerts to show that face when it appears on any camera, correlated with maps, so responders can help neutralize any threat. Schools can share the highlighted video with law enforcement, so they have an
accurate picture of the intruder before they arrive on the scene. Audio analytics should also be included as standard in any campus setting. If a separate purpose-built audio system is beyond the budget, it’s important to be aware that many modern AI-based cameras also support audio analytics that can detect glass breaks, gunshots, screams, and explosions. These audio alerts can provide additional
validation and verification about events taking place.
Deploying a Successful AI-based Video Surveillance System
With all the power and potential of an AI-based video system, it’s important to realize that not all systems are the same. The implemen- tation of the technology can vary widely between manufacturers and might not be appropriate for campus security use cases. For example, some AI-enabled cameras only detect objects but not the attributes that distinguish those objects from others. Make sure the system you invest in can detect colors and other attributes, and lets you store this data, called metadata, along with the video. The type and number of attributes that are captured also varies. There are very few systems in the market that can detect shoe color, for example, which has been a particular request for K–12 use cases.
Most importantly, the descriptive metadata captured from an AI-based camera is only useful if it can be interpreted and displayed within a customer’s chosen VMS or network video recorder (NVR). It’s imperative to ensure a “match” between an AI-enabled camera and the VMS. The VMS must be able to search or react to all the AI metadata it receives beyond simply displaying the video. For example, i-PRO’s Active Guard plug-in unlocks forensic search capabilities by delivering an unprecedented number of attributes to popular VMSs such as Genetec, Milestone, and Video Insight.
A new type of analytic called scene-change detection is perfect for
π
OFFICE ESSENTIALS
COMPLETE CATALOG
1-800-295-5510 uline.com
CHAIRS
FILE CABINETS
Untitled-3
1
ORDER BY 6 PM FOR SAME DAY SHIPPING
DESKS AND TABLES
CHAIR MATS
JULY/AUGUST 2023 campuslifesecurity.com 21 6/9/23 4:44 PM