Metadata is information that describes object-related content in the camera FOV.

In Axxon One, metadata can be obtained in two ways:

  1. By analyzing video stream on Server by detection tools.
  2. By receiving metadata from camera embedded analytics (see Embedded Detection Tools). 

To get metadata from video, you have to de-compress and analyze the video stream, which increases the load on the Server, thus limiting the number of available camera channels.

The following tools are used for the Server-side analysis and metadata generation:

  1. Object Tracker.

  2. Neural Tracker.

    Object tracker and Neural Tracker generate metadata containing the following information about moving objects in FOV: object type, position, size and color, motion speed and direction, etc.


  3. Motion detection.

    Motion detection generates less accurate data. It does not detect object type and color.


  4. Category: Face.

    Face detection metadata contains face bounding boxes and their positions, as well as face vectors.


  5. License Plate Recognition.

    License Plate Recognition metadata contains license plate bounding boxes and their positions in the frame, as well as vehicle license plate.


  6. Vehicle Recognition.

    Vehicle Recognition metadata contains vehicle bounding box that is built around vehicle outline, position of the vehicle bounding box in the frame, information about the vehicle model, manufacturer, color, and class.

  7. Pose detection.

    Metadata from pose detection tools contains information on positions and pose (skeleton) of all people in FOV. 


  8. Equipment detection (PPE).

    Equipment detection metadata contains information about the position of all people in FOV.


  9. Barcode Detection.

    Metadata from the Barcode Detection contains information about the contents of all barcodes in the frame.

The metadata is used for the following system options:

Option

Required source of metadata

Scene Analytics

Object Tracker, Neural Tracker, Embedded Detection Tools, or Motion detection

Forensic search MomentQuest

Object Tracker, Neural Tracker, Embedded Detection Tools, Motion detection, Category: Face, Category: Vehicle, Pose Detection, Equipment detection (PPE)

Face search

Category: Face

Search by LPs

Category: Vehicle

TimeCompressor

Object Tracker, Neural Tracker, Embedded Detection Tools, or Motion detection

Tag&Track Pro

Object Tracker, Neural Tracker, Embedded Detection Tools, or Motion detection

Object tracking

Any

Autozoom

Any

Search by barcode

Barcode Detection


If a camera uses several sources of metadata, the required source is selected automatically, except for MomentQuest.

To perform face/license number searches, only metadata from corresponding detection tools is used.

By default, metadata is stored as files in the object tracks database in the local Server directory that was selected when installing Axxon One (see Installation) in the vmda_db\VMDA_DB.0\vmda_schema subfolder.

If necessary, you can place metadata on any available network storage (see Configuring storage of the system log and metadata).