Join or Sign in

Register for your free asmag.com membership or if you are already a member,
sign in using your preferred method below.

To check your latest product inquiries, manage newsletter preference, update personal / company profile, or download member-exclusive reports, log in to your account now!
Login asmag.comMember Registration
https://www.surveycake.com/s/xGmOz
INSIGHTS

Noonlight upgrades video monitoring solution with AI person filtering and advanced verification

Noonlight upgrades video monitoring solution with AI person filtering and advanced verification
Two new capabilities cut video noise, reduce false dispatches, and accelerate issue resolution, without missing real emergencies.
Noonlight, an innovator in intelligent emergency response and professional monitoring solutions, today announced two new features for its Verify API which powers its video monitoring solution, designed to help commercial and residential video security providers deliver smarter, more proactive protection to their end users.  
 
Verify adds a human verification layer to video-triggered events, enabling trained Noonlight agents to review incidents before emergency response is dispatched. By pairing advanced analytics with professional monitoring, Verify reduces non-actionable video noise and helps agents resolve real threats faster – without increasing operational burden or false dispatches.  
 
The new Verify features include AI Person Filtering, which automatically screens incoming video events and dismisses clips with no person detected, eliminating the cost and time of reviewing empty motion alerts. When an event is escalated to a live monitoring agent, Advanced Verification provides deeper context through extended footage and live camera access, along with the ability to deter a situation in real time before an alarm is ever created. The result is fewer disruptions for end users, fewer unnecessary police dispatches, and faster alarm resolution when it matters most.  
 
"The burden of responding to an emergency should never fall on the end user, and unnecessary disruptions should never affect the people our partners are trying to protect,” said John Tassone, President of Noonlight. “What we’ve built is a smarter way to deliver the right context to agents at exactly the right moment — so they can filter out the noise, act decisively on real situations, and prevent emergencies from escalating wherever possible. That’s what automatic safety looks like in practice.” 
 

AI person filtering 

Noonlight uses a proprietary AI model to scan all incoming video clips and automatically dismiss any event where no person is detected, ensuring that non-actionable footage is never sent to monitoring agents. By scanning all the video, and processing hundreds of frames per clip, Noonlight’s AI model is designed to detect even brief human appearances, delivering 99% recall and 97% precision – meaning it almost never misses a person and is almost always correct.  
 
For partners already using AI-based filtering, Noonlight’s model delivers incremental noise reduction, particularly in outdoor environments, while supporting vendor consolidation and reducing integrations to manage.  
 

Advanced verification 

Events that require video verification often do not require emergency dispatch. Advanced Verification enhances Noonlight’s existing verification workflow by enabling agents to access additional context, including extended footage captured up to 90 seconds before the event and a live camera look-in.  This enables them to more quickly identify potential threats or emergency events.  
 
When appropriate, agents can also initiate active deterrence through talkdown directly via the camera – de-escalating situations before alarms are triggered, and emergency response is dispatched.  
 
This deeper context results in faster intervention and a better user experience without compromising safety and security.  Early data indicates that advanced verification with talkdown reduces total false alarms by 45%. In 37% of cases, the person left the scene on their own and in 8% of cases, agents determined the person was an authorized employee – preventing unnecessary alarms while ensuring real threats are not missed. 
 


Product Adopted:
Software
Subscribe to Newsletter
Stay updated with the latest trends and technologies in physical security

Share to: