Loading ...
Loading ...
Loading ...
Fig. 57: Configuration of AI-CROWD
The configuration section provides the following functions:
Add Sensor: Click this button to draw a virtual sensor with the mouse method “click and drag”. The sensor
can be moved and changed in its size, by dragging the nodes. You can direct the sensor (the counting
direction is given by the arrow), for example rotating the sensor until the arrow points to the desired
direction, or specify if the sensor is monodirectional rather than bidirectional .
Remove sensor: Click this button to remove the selected sensor from the configuration.
Redraw the sensor: Click to delete the current sensor and draw a new one.
ID sensor: define an IDnumber for the sensor.
Sensor name: this name uniquely identifies the main counting sensor (green arrow); is used to generate
counting events, sent, for example, to AI-Dash.
Event period(s): interval in seconds between two consecutive events that need to be sent to an external
server.
Enable crowd estimation:check to activate AI-CROWD.
AI-OVERCROWD
AI-OVERCROWD is avideo analytic app that can be used to detect overcrowding inside one or more areas of
interest in typical retail scenarios; of course, the position of the camera and the environmental conditions
will affect the performance of the application.
The accuracy to be expected is 90% under ideal environmental and installation conditions.
Fig. 58: AI-OVERCROWD
AI-RETAIL3
AI-OVERCROWD
95 / 153
Loading ...
Loading ...
Loading ...