Vehicle Make and Model Recognition

Identifies the manufacturer and model of vehicles detected during number plate recognition.

Media Server has been pre-trained to recognize the manufacturer of vehicles. If you also want to identify the model of a vehicle, you must train vehicle model recognition.

Configuration Parameter Description
ColorRegion Specifies what to output to the ColorRegionWithSource output track, so that you can use color clustering to identify the color of the vehicle.
Database The database to use to identify the vehicle model.
DetectEveryFrame Specifies whether to use every frame in which a vehicle is present to improve the accuracy of detection.
FieldOfView The horizontal angle of view of the camera, in degrees.
Input The name of the track to analyze.
MaxPerspectiveError The maximum percentage difference, between the size of a recognized vehicle and known dimensions for that vehicle model.
MinGrillePercentage The minimum amount of the vehicle grille that must be visible in the image to attempt vehicle identification.
MinPerspectiveData The minimum number of data records that must be generated before attempting to calculate the perspective.
NumParallel The maximum number of video frames to analyze simultaneously.
Perspective Specifies whether source images are affected by perspective transformations.
SegmentDuration The maximum duration of a record in the SegmentedResult or SegmentedResultWithSource track.
SyncDatabase Specifies whether to synchronize with the training database before beginning the analysis task.
Type The analysis engine to use. Set this parameter to VehicleModel.
VehicleMakeRecognitionThreshold The minimum confidence that must be achieved for successful recognition of the vehicle make.
VehicleModelRecognitionThreshold The minimum confidence that must be achieved for successful recognition of the vehicle model.
WorldDimensions A list of dimensions that describe the actual size of a vehicle model or vehicle type.
WorldDimensionsMetadata The name of a metadata field that describes the actual size of a vehicle model.

Output Tracks

The following table describes the tracks that are generated by this engine. The Output column indicates whether the information contained in the track is included by default in the output created by an output task (when you don't set the Input parameter for the output task).

Output track Description Output
Data Contains one record, describing the analysis results, for every input record. No
DataWithSource

The same as the Data track, but each record also includes the source frame.

No
Result Contains one record, describing the analysis results, for each vehicle. When the same vehicle appears in consecutive frames, Media Server produces a single result. Yes
ResultWithSource

The same as the Result track, but each record also includes the best source frame.

No
SegmentedResult

(Available only when processing video). The same as the Result track, except the duration of each record is limited by the parameter SegmentDuration. If a result exceeds the specified duration, Media Server begins a new record with the same ID.

Yes
SegmentedResultWithSource

(Available only when processing video). The same as the ResultWithSource track, except the duration of each record is limited by the parameter SegmentDuration. If a result exceeds the specified duration, Media Server begins a new record with the same ID.

No
ColorRegionWithSource This track can be passed to a color clustering task, to determine the color of the vehicle. The data contained in the track varies based on the value of the ColorRegion parameter. No
VehicleMakeImage Contains one record for each vehicle. Each record includes a scaled image of the grille patch that is used to identify the vehicle make. The purpose of this track is to produce images for training vehicle makes. No
WorldData These tracks are similar to the Data, Result, and SegmentedResult tracks, respectively. The difference is that each record also contains the approximate position of the vehicle in real-world 3D coordinates. These tracks are available only when you set the Projection parameter or configure Media Server to calculate a perspective projection matrix. For more information about using perspective in media analysis, refer to the Media Server Administration Guide. No
WorldResult No
WorldSegmentedResult No

For more information see Vehicle Make and Model Recognition Results or use the action GetExampleRecord.