iSentry - Real-Time Unusual Behavior Detection
iSentry is designed to analyse CCTV cameras, efficiently and in real time to give controllers only what they need to see, immediately in the form of video that is enriched with multiple data points.
Unusual Behaviour detection is driven by an unsupervised Artificial Intelligence platform. Pixel based analysis allows the system to learn how objects normally move in an environment. After a norm is established for a particular scene, the system will then create an event on any exceptions.
For sterile environments or specific areas of a video scene, multi-directional video tripwires (VTW) will alert on all moving objects within the specified area.
Left or Stationary Object Detection will create an event when an object enters a scene and remains stationary for more than a predefined amount of time.
These events are then classified using Deep Learning tools and a logic engine for further contextualisation.