Our usual location algorithm creates events when there are people and vehicles in an unusual location within the scene at that time. Some examples of the types of events that this algorithm finds are:
Vehicles driving on footpaths
People accessing rail tracks/tunnels
Intruders climbing over perimeter fences
Maintenance workers on ladders
Children falling/playing on escalators or fountains
People on motorways
People accessing “no-go” zones
Suspicious behaviour
Vandalism
Camera tampering
Vehicle driving over median strip at carpark
Fare evasion
Aggressive behaviour (pushing into unusual area)
Tunnel Trespassing
A typical scene will have areas of common movement and areas that remain relatively static for much of the day. The unusual location algorithm determines the areas of the scene that it is usual for people and vehicles to be. A day is modelled from an earlier period that may be from the day before, a week earlier or a range of days of data. The system constantly updates this model to establish the expected location of people / vehicles in a scene at any given time and will raise an event when they are located in an area that is not expected.
