Machine-learning technology from Nokia is helping to identify emergencies and criminal activity such as vandalism and drug trafficking in real time.
Information management specialist Room40 has adopted Nokia Scene Analytics in its video and audio security monitoring analytics solution to increase security and safety at a range of different sites across Belgium, including service stations, car parks and construction sites.
Nokia’s software processes thousands of simultaneous streams from existing CCTV infrastructure as well as new audio and IoT sensors, and sends real-time incident alerts to security teams.
This improves the monitoring of facilities like motorway service stations, which are often the site of vandalism, theft and coordinated drug and human trafficking, but which find the cost of 24/7 video and audio monitoring, either by personnel or software, prohibitively expensive.
Room40 is working with Vias Institute, the Belgian knowledge centre for road safety and security, to tackle this issue in Belgian service stations and other public spaces using the Nokia Scene Analytics solution. The same solutions will also be made available for construction firms to monitor productivity and safety on-site.
So how does it work?
Typically, up to 99% of video, audio and sensor data records normal behaviour. Instead of having to be programmed to recognise security scenarios, Nokia Scene Analytics uses machine learning to establish what is ‘normal’. It then tracks and records only irregular behaviour that might be connected to safety or security incidents. This reduces the amount of data that needs processing and more quickly and efficiently alerts personnel to incidents, Nokia explained.
Superfast, always-on, ubiquitous connectivity will ramp up the potential for AI tools to respond immediately to real-time data. Download our Next-generation connectivity report to learn more!
Tags: CCTV, IoT sensors