Versions Compared

Old Version 7

changes.mady.by.user Alena Kniazeva

Saved on

compared with

New Version 8

changes.mady.by.user Alena Kniazeva

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Metadata is any accompanying data to any basic information. Metadata refers to additional information about the content or object. It reveals information that describes the behavior of objects in the camera FOVabout the attributes and properties that characterize an entity, allowing you to automatically search and manage it in large information flows.

In Axxon One, you can get metadata in two ways:

  1. By analyzing video on the Server by detection tools (see General information about detection tools and their sub-tools).
  2. By receiving ready metadata from the embedded camera analytics (see Embedded Detection Tools). 
Note
titleAttention!

To get metadata, video is decompressed and analyzed, which leads to a heavy load on the Server and limits the number of cameras that you can use on it.

Metadata are VMDADB files and are stored in the object tracks database. Path to the metadata folder: <Local directory of the Server selected when installing Axxon One (see Installation)>\vmda_db\VMDA_DB.0\vmda_schema.

Info
titleNote

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

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

Detection toolInformation Possible information about an object contained in metadata from the detection tool tool
Neurotracker
  • Object type
  • Object size
  • Object color
  • Position of an object in the frame
  • Object speed
  • Direction of movement of an object
Metadata from Object Tracker and Neurotracker contains the following information about all objects moving in the frame: object type, position in the frame, size and color, speed, direction of movement, and so on


Object Tracker
Motion detectionMetadata from Motion
  • Object type
  • Object
detection is less accurate and doesn't contain information about object type and
  • color


Face Detection VA
  • Face vector
  • Face bounding box
  • Gender
  • Age
  • Position of a face bounding box in the frame
Metadata from Face Detection contains a face bounding box, its position in the frame, and a face vector
Face Detection TV
Face Detection VL
License Plate Recognition BRS
  • Vehicle license plate
Metadata from License Plate Recognition detection tools contains
  • License plate bounding box
  • Position of a license plate bounding box
, its position
  • in the frame
, and a vehicle license plate
  • Direction of vehicle movement
  • Region
  • Country
  • License plate type
  • Vehicle manufacturer
  • Vehicle model
  • Vehicle color
  • Vehicle class
  • Vehicle bounding box
  • Position of a vehicle bounding box in the frame
License Plate Recognition IV
License Plate Recognition RR
License Plate Recognition RR—Search In Archive
License Plate Recognition RR—Parking
License plate recognition (VT)
Vehicle Recognition RR
  • Vehicle manufacturer
  • Vehicle model
  • Vehicle color
  • Vehicle class
  • Vehicle bounding box
  • Position of a vehicle bounding box in the frame
  • Direction of vehicle movement
Metadata from Vehicle Recognition contains a 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

Pose Detection and its sub-tools:

  • Position of an object in the frame
  • Pose of an object
Metadata from Pose Detection tools contains information about positions and pose (skeleton) of all people
  • in the frame
Equipment detection tool (PPE)Metadata from Equipment detection contains information about the position of all people in
  • Position of an object in the frame
PPE detection VL
Barcode DetectionMetadata from Barcode Detection contains information about the contents of all barcodes
  • Contents of a barcode in the frame

Metadata is used for the following system options to work:

Option

Required source of metadata

Standard detection sub-tools

, , or Motion detection

Forensic search MomentQuest

,  Embedded Detection Tools, Motion detection, Category: Face, Category: Vehicle, Pose Detection, 

Face searchCategory: Face

Search by LPsCategory: Vehicle

Search by barcode

TimeCompressor

, Neurotracker, 

Functions for tracking of moving objects, or Motion detectionTag&Track Pro

, Neurotracker, , or Motion detection

Object tracking

Any

Autozoom

Any

Search by barcode

Barcode Detection

Note
titleAttention!

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

To perform face/license plate search, only metadata from the corresponding detection tools is used.

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.

...

titleNote

...

Object tracking

Autozoom

...