Overview

The Presence Monitor node tracks how long each detected, tracked object has been present in the specified region in the video, can highlight objects and generate max time/occupancy level alarms, and adds the presence metadata to the frame metadata. It is designed for monitoring use cases.

This node generates presence metrics: current occupancy, objects above max time threshold, occupancy above/below max thresholds.

This node requires a AI Model Node and a Track Objects Node before it in order to function properly.

This node is a simplified version of the Occupancy Monitor. Use the Occupancy monitor if you need to collect statistics such as wait times, people flow, etc. for dashboards, reporting and business intelligence.

Inputs & Outputs

• Inputs : 1, Media Format : Raw Video
• Outputs : 1, Media Format: Raw Video
• Output Metadata : Presence Information

Properties

Events

Triggering specific events using trigger_events and event_template fields allows you to add Events to metadata. These Events can then be processed by downstream nodes to publish metrics to a Dashboard, or send notifications or trigger alarms / bookmarks.

Output Metadata

The fields below are declared by this node's metadata schema; the JSON values are representative examples.

JSON example

{
  "nodes": {
    "annotate_presence1": {
      "events": [],
      "events_delta": 0,
      "rois": {
        "roi1": {
          "all_objects_not_present_delta": false,
          "all_objects_present": true,
          "all_objects_present_delta": false,
          "coords": [
            [
              468,
              172
            ],
            [
              597,
              307
            ]
          ],
          "current_occupancy": 1,
          "description": "value",
          "objects_above_max_occupancy_count": 0,
          "objects_above_max_waiting_time_count": 1,
          "objects_above_max_waiting_time_delta": 0,
          "objects_below_max_occupancy_count": 0,
          "objects_entered_delta": 0,
          "objects_exited_delta": 1,
          "objects_flagged": [
            "12837198712897",
            "1231293712897612"
          ],
          "objects_flagged_count": 0,
          "objects_flagged_delta": 0,
          "objects_of_interest_keys": [],
          "occupancy_above_max_threshold_delta": 0,
          "occupancy_below_max_threshold_delta": 0
        }
      },
      "type": "annotate_presence"
    }
  }
}

Object labels and attributes

• Object labels/classes added: No new class is created. The node can reinsert a tracked upstream object, preserving its original label and class.
• Object attribute labels/classes added: Depending on add_object_attributes, the presence state (enter, exit, or max_wait) uses class 35101, the ROI label uses class 35102, and <ROI>_<state> uses class 35103.