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 Media Server to recognize vehicle models. For information about training Media Server, refer to the Media Server Administration Guide.
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
Output track | Description | Output1 |
---|---|---|
Data
|
Contains one record, describing the analysis results, for every input record. | No |
DataWithSource
|
The same as the |
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 |
No |
SegmentedResult
|
(Available only when processing video). The same as the |
Yes |
SegmentedResultWithSource
|
(Available only when processing video). The same as the |
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.