Object Recognition Results

The following XML shows a single record produced by object recognition.

<output>
  <record>
    ...
    <trackname>object.Result</trackname>
    <ObjectRecognitionResult>
      <id>ed1f3af7-9f00-434f-8bc4-a328ff4c67fc</id>
      <identity>
        <identifier>MicroFocus</identifier>
        <database>logos</database>
        <confidence>100</confidence>
        <metadata>
          <item>
            <key>CompanyName</key>
            <value>MicroFocus</value>
          </item>
        </metadata>
      </identity>
      <boundary>
        <point>
          <x>106</x>
          <y>100</y>
        </point>
        <point>
          <x>271</x>
          <y>101</y>
        </point>
        <point>
          <x>272</x>
          <y>183</y>
        </point>
        <point>
          <x>107</x>
          <y>183</y>
        </point>
      </boundary>
      <parentID>4d69390f-a8c4-4c5d-a0b0-705a3f98aa9b</parentID>
    </ObjectRecognitionResult>
  </record>
</output>

The record contains the following information:

  • The id element provides a unique identifier for the recognized object. Media Server issues an ID for each appearance of an object. If you are recognizing objects in video and consecutive frames show the same object in a near-identical location, all records related to that appearance will have the same ID.

    For example, if an object appears in the same location for a hundred consecutive video frames, the engine uses the same ID for each record in the data track and the single record in the result track. The record in the result track will have a timestamp that covers all of the frames.

    If the object disappears and then reappears, the engine considers this as a new detection and produces a new ID and a new record in the result track.

  • The identity element represents a match between the ingested media and an object in your training database.

    • The identifier element provides the identifier of the object that was detected in the ingested media.
    • The database element provides the name of the database in which the object exists.
    • The confidence element provides the confidence score for the match (from 0 to 100).
    • The metadata element provides metadata that you associated with the object when you trained Media Server. If there is no metadata in the training database, this element is omitted.
  • The boundary element provides the position of the object in the ingested media, as a set of points that form a polygon which surrounds the object.
  • The parentID element is empty, unless you configure the analysis engine with Region=Input in which case it contains the UUID of the input record. This provides a way to link the result with other records (from another analysis task) that supplied the region to analyze. To generate a single record combining the information, you can use the Combine ESP engine and the example Lua script parentuuidMatch.lua.