Identify Vehicle Models

To identify vehicles in video, use the following procedure.

To identify vehicles

  1. Create a new configuration or open an existing configuration to send to Media Server with the process action. Alternatively, you can modify the Media Server configuration file (mediaserver.cfg).

  2. In the [Analysis] section, add a new analysis task by setting the AnalysisEngineN parameter. You can give the task any name, for example:

    [Analysis]
    AnalysisEngine0=ANPR
    AnalysisEngine1=VehicleModel
  3. Create a new configuration section to contain the task settings, and set the following parameters:

    Type The analysis engine to use. Set this parameter to vehiclemodel.
    Input The track to process. This track must be the DataWithSource or ResultWithSource track from a number plate analysis task.
    Database The name of the object database to use to identify vehicles. For information about creating this database, see Train Media Server to Recognize Vehicles.
    Perspective (Optional) If the video frames show the vehicle from a different perspective to that used in the training images, set this parameter to TRUE so that Media Server compensates accordingly.
    ColorRegion (Optional) The region to output to the ColorRegionWithSource output track, so that you can configure an analysis task to identify the color of the vehicle. If you don't specify a region, Media Server uses a default region.

    For example:

    [VehicleModel]
    Type=vehiclemodel
    Input=ANPR.DataWithSource
    Database=vehicles
    Perspective=FALSE

    For more information about the parameters that you can use, including the values that they accept, refer to the Media Server Reference.

  4. Save and close the configuration file. If you modified the Media Server configuration file, you must restart Media Server for your changes to take effect.


_HP_HTML5_bannerTitle.htm