VehicleAnalysis

Runs number plate recognition, vehicle recognition (make and optionally model), and vehicle color analysis on the file(s) associated with an IDOL document FlowFile, and adds information about vehicles to the IDOL document.

To recognize vehicle models you must train a vehicle model database. For more information about vehicle analysis, including how to train a vehicle model database, refer to the Media Server Administration Guide.

Properties

Name Default Value Description
IDOL License Service   An IdolLicenseServiceImpl that provides a way to communicate with an IDOL License Server.
Media Service   A MediaServiceImpl that manages media analysis resources.
Number Plate Locations   A comma-separated list of ISO-3166 codes to specify the locations for which you want to recognize number plates.
Database File   The path of a file that contains the vehicle model database to use. Set this property to use a database that you exported from Media Server, using the action ExportVehicleModelDatabase.
Shared Database   The name of the vehicle model database to use. Set this property to use a database that is stored in the external database specified by the Media Service (see the "Media Service" property).
Image Output Format   When set, the processor saves the full image or best video frame for each detected vehicle, in the specified format (BMP, GIF, JPEG, PDF, PNG, PPM, TIFF or WEBP).
Video Clip Quality   When set to "low", "medium", or "high", the processor saves a video clip of the detected vehicle at the specified quality level.
Video Clip Height 300 The height of the video clip that is generated when you set Video Clip Quality, in pixels.

Relationships

Name Description
success Processing was successful.
failure Processing failed.

Example Output

The following examples show the metadata that can be added to an IDOL document by vehicle analysis.

The XML contains a vehicle element for each vehicle.

  • The numberplate element provides information about the number plate.

    • plateread - the characters from the number plate.
    • origin - the country of origin.
    • region - the position of the number plate in the image.

      When you analyze an image or document the page attribute specifies the page on which the number plate was detected. When you analyze a video and a number plate is tracked across multiple frames, there can be multiple region elements with start and duration attributes that provide video timestamps, in seconds.

      The point elements describe the corners of a polygon that contains the number plate. All of these values are in pixels, where x=0, y=0 represents the top-left corner of the image.

      The left, top, width, and height attributes describe the position and size of a bounding box around the polygon (left specifies the distance from the left side of the image to the left side of the region, and top specifies the distance from the top of the image to the top of the region).

    • subread - the sub-read from the number plate. This field is only used for some locations, such as the United Arab Emirates. If the number plate does not have a sub-read, the element is omitted.
    • vehicletype - the vehicle type (private, taxi, military, and so on), if it can be determined from the number plate. If the number plate does not contain this information, the element is omitted.
  • The make and model elements describe the vehicle make and model. The model is present only if you have trained and configured a vehicle model database.
  • The color element describes the vehicle color. The r, g, and b attributes give the red, green, and blue color components.
  • The videoFile element contains the path of the video file that is generated when you set the property Video Clip Quality.
  • The bestRegion element represents the best video frame in which the vehicle was visible. It includes the region element for that frame, but can also include:

    • imageFile - The path of the image that was generated when you set the property Image Output Format.
  • The region element describes the location of the vehicle in the image.

    When you analyze an image or document the page attribute specifies the page on which the vehicle was detected. When you analyze a video and a vehicle is tracked across multiple frames, there can be multiple region elements with start and duration attributes that provide video timestamps, in seconds.