Skip to main content
Version: 2.3.1

Output Data Formats

OMNI Agent converts the results of video processing into the formats of processes and events for subsequent sending to OMNI Platform or third-party services.

Processes​

A process is one of the formats for representing recognition and tracking results implemented within time intervals.

Each process contains the following set of data:

  • Process ID;
  • Process time interval (start and end of the process);
  • Process type (track, human, face, body, emotion etc.);
  • Detection object with face attributes (object is a human in the camera’s field of view);
  • Best shot.

Processes are sent to OMNI Platform via the HTTP protocol or to an external service via a webhook.

Events​

An event is a format for presenting identification results, generated by OMNI Agent and transferred to OMNI Platform for subsequent sending to a third-party service via a web socket.

Depending on the identification results, OMNI Agent can send two types of events: identification events (the person from the camera is identified) and non-identification events (the person from the camera is not identified).

Structure of non-identification event:

type - non_identification

camera:

  • id - camera identifier
  • type - camera type
  • title - camera title
  • width - frame width
  • height - frame height
  • stream - rtsp-stream address
  • real_name - original name
  • agent_id - agent identifier

event:

  • id - event identifier
  • detection_date - detection date
  • image - face crop identifier
  • original_image - original image identifier
  • image_link - link to the face crop
  • original_image_link - link to the original image

Structure of identification event:

type - identification

camera:

  • id - camera identifier
  • type - camera type
  • title - camera title
  • width - frame width
  • height - frame height
  • stream - rtsp-stream address
  • real_name - original name
  • agent_id - agent identifier

candidates (profiles with which identification occurred):

  • profile:

    • id - profile identifier
    • age
    • gender
    • navatar_id - identifier of profile avatar
    • main_sample_id - main sample identifier
    • sample_link - link to the main sample

  • profile_groups:

    • id - identifier of the group which the profile is linked to
    • color - color of the group which the profile is linked to

  • confidence - the degree of similarity of the face from the frame with the candidate (from 0 to 1)

event:

  • id - event identifier
  • detection_date - detection date
  • image - face crop identifier
  • original_image - orginal image identifier
  • image_link - link to the face crop
  • original_image_link - link to the original image