Are business alarms set to change forever? Nirovision, an Australian trailblazer in AI-powered video analytics unveiled its latest breakthrough, Safety Agent Alarm, a world-first innovation that allows an AI agent to actively monitor a workplace’s security cameras and promptly alert for security and safety concerns.
With AI analysing footage in real-time, the Safety Agent is smart enough to distinguish between non-events and genuine safety concerns but can also be given custom prompts and extra knowledge such as “Hi-vis vests are mandatory on-site” to ensure adherence to specific safety rules.
Unlike traditional business alarms which are limited to basic motion detection, Safety Agent Alarm empowers workplaces to be notified of events that were previously deemed impossible.
These are just a few examples of the different kinds of alerts Safety Agent Alarm can detect:
● Alert for someone lying on the ground.
● Alert for someone on the roof near the edge.
● Alert if a worker looks injured.
● Alert for people physically fighting.
● Alert for a person climbing a fence.
● Alert for a vehicle load not suitably restrained.
● Alert for someone who seems trapped eg. in a cool room.
As a company that develops its own AI models in-house, Nirovision has already seen the impact its technology is having on workplaces. Whether it is automating site access or enforcing compliance, the addition of the Safety Agent Alarm is another exciting AI development that is set to revolutionise workplace monitoring.
“We believe AI is poised to redefine incident monitoring so the future is exciting,” says Jimmy Lee, Nirovision’s CEO. “Today, multimodal large language models are capable of recognising and discerning what it sees and transcribing its observations in great detail. This, in concert with our efficient object detection models, allows workplaces to receive descriptive alerts for previously unseen safety and security events in real-time.”
Recognising the distinct safety requirements of every workplace, Lee emphasises, “It was only a matter of time before these large vision models infiltrated the camera monitoring space so we are proud to be pioneers in bringing this to market.”
