Noonlight has unveiled enhancements to its Verify API, a tool integral to its video monitoring system. These advancements are aimed at empowering both commercial and residential security providers with more intelligent and proactive protection solutions.
Verify incorporates human verification for video-triggered events, facilitating review by trained Noonlight agents before any emergency response is initiated.
This integration of advanced analytics with professional monitoring serves to lower the occurrence of non-actionable video alerts and equips agents to address actual threats more swiftly, without increasing operational workload or the number of false dispatches.
AI Person Filtering and Advanced Verification Features
Among the new additions to Verify are AI Person Filtering and Advanced Verification. The AI Person Filtering feature automates the screening of video events, discarding clips where no person is detected. This innovation reduces both the cost and time associated with reviewing irrelevant motion alerts.
Meanwhile, Advanced Verification offers agents enhanced context through access to extended footage and live camera feeds, allowing them to actively address situations in real-time before an alarm is generated. These updates lead to fewer disruptions for users, fewer unwarranted police dispatches, and expedited alarm resolution when it truly matters.
Focus on Preventing Escalation
Noonlight’s AI discards video clips without detectable human presenceJohn Tassone, President of Noonlight, emphasized, "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. 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."
Effectiveness of AI Person Filtering
Noonlight’s proprietary AI model meticulously reviews incoming video clips, instantly discarding clips with no detectable human presence. Processing hundreds of frames per clip, this model offers a 99% recall and 97% precision rate, ensuring nearly all human appearances are identified accurately.
For partners utilizing AI-based filtering, Noonlight’s model contributes further noise reduction, especially in outdoor settings, simplifying vendor integrations and management.
Advanced Verification Workflow
Events often deemed necessary for video verification may not require emergency dispatch. Noonlight's Advanced Verification feature enriches the existing framework by providing agents with additional context, such as footage lasting up to 90 seconds before an event and live camera access.
This enhanced insight enables quicker identification of potential threats or emergencies. When needed, agents can also engage in active deterrence through real-time communication via the camera, thereby de-escalating issues before triggering alarms or necessitating emergency responses.
This comprehensive context allows for more rapid intervention and improves user experience without sacrificing safety. Preliminary data reveals that implementing advanced verification with talkdown reduces false alarms by 45%.
In 37% of situations, individuals departed on their own accord, and in 8% of cases, agents verified the presence of authorized employees, effectively preventing unnecessary alarms while ensuring that genuine threats are not overlooked.
