FortiCentral supports object detection in video analytics. Important detected objects, such as people, guns, or cars, are fed into the database of a FortiRecorder where they are used to trigger notifications and then forwarded to all FortiCentral workstations.
To configure object detection
- Select the settings button in the camera’s pane window.
- Select Analytics.
- Select Object Detection in Video from the Algorithm dropdown menu.
- Enable Visualize to display a bounding box around the detected object in the camera preview.
- Enable Detailed Analysis if a more detailed analytics network is required. Keep in mind enabling this feature will decrease processor speed.
- Select the type of object you want to detect from the These Types dropdown menu.
- Select the desired detection area. A detection area limits the space to scan for object detection. ROI areas define a special area of focus using a user-defined bounding square. The Mask type creates a black out zone where object detection does not scan.
- Select Apply and then OK.
To blur specific objects like a license plate, see the Privacy AI filter section in the Facial Recognition chapter.