Watch less, see only the unusual events, in real time

Unusual Behaviour is designed to add instant visual insight (much like a human eye) to the huge amounts of footage generated by a large scale CCTV deployment

Looking for help? Get in touch with us

See only the unusual events

Unusual Behaviour (UB) detection is driven by an unsupervised Artificial Intelligence platform.

Pixel-based analysis allows the system to learn how objects normally move in an environment taking into account direction, speed, size and a variety of other factors. After a norm is established for a particular scene, the system will then create an event on any exceptions. These events are then classified using Deep Learning tools and a logic engine for further contextualisation.

iSentry Unusual Behaviour is designed to add instant visual insight (much like a human eye) to the huge amounts of footage generated by a large scale CCTV deployment.

The self learning goes very fast. Depending on the complexity of the scenery, the self learning engine starts getting a smart isight of what is usual after 48 – 72 hrs of operation.

Watch less

Operators view video on an event basis, not a constant stream. The total amount of video to be seen is reduced to less than 1%. One operator seat can monitors 300+ cameras, implying savings in the control room.

It generates a higher detection rate, eliminated human errors, eliminates missed events and maintains alertness

In Real time

Contrary to many other systems, iSentry monitors all CCTV channels in real time and provides the operator within milliseconds about alerts, potentially leading to a justified alarm or escalation procedure

Examples of UB detection

Irregular Movement

Criminal Behaviour

Fire & Smoke Detection