To identify vehicles in video, use the following procedure.
To identify vehicles
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
).
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
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.
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.
|