Train Media Server to Recognize Vehicle Models

Vehicle recognition identifies both the make and model of a vehicle detected by number plate recognition.

Media Server has been pre-trained to identify the make of vehicles, but you must train Media Server to recognize vehicle models by providing images of those models.

The following diagram shows how Media Server stores information about vehicle models.

The "Media Server database" represents the Media Server datastore file or a database on an external database server. For information on setting up this database, see Introduction.

You can organize vehicle models into databases. These databases are for organizational purposes. For example, you might have a database for European vehicle models, and a database for American vehicle models. When you run vehicle recognition, you must choose the database to use.

A database can contain any number of vehicle models. You must associate a vehicle make with each model. After Media Server identifies the make of a vehicle it can then perform recognition against a much smaller number of models.

To each vehicle model you must add at least one training image. Vehicle manufacturers update the design of their models over time, and might offer vehicles in different configurations. You can choose whether to consider these the same model or train different models.