This analysis task 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.
This section describes the parameters that you can use to configure vehicle make and model recognition.
Configuration Parameter | Description |
---|---|
ColorRegion | Specifies the region to output to the ColorRegionWithSource output track, so that you can configure an analysis task to identify the color of the vehicle. |
Database | The name of the database that contains known vehicle models. |
DetectEveryFrame | Specifies whether to use every frame in which a vehicle is present to improve the accuracy of detection. |
Input | The name of the track to analyze. |
MinGrillePercentage | The minimum amount of the vehicle grille that must be visible in the image to attempt vehicle identification. |
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. (Available only when processing video). |
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. |
Output track | Type | Description | Output1This 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). |
---|---|---|---|
ColorRegionWithSource
|
VehicleColorRegionAndImage | Describes a region that is expected to contain a sample of the vehicle color. The track also contains the source image. You can use this track with another engine to determine the color of the identified vehicle. | No |
Data
|
VehicleModelResult | Contains one record, describing the analysis results, for every input record. | No |
DataWithSource
|
VehicleModelResultAndImage | The same as the Data track, but each record also includes the source frame. |
No |
Result
|
VehicleModelResult | 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
|
VehicleModelResultAndImage | The same as the Result track, but each record also includes the best source frame. |
No |
SegmentedResult
|
VehicleModelResult | (Available only when processing video). Contains one or more records, describing the analysis results, for each vehicle. The maximum duration of records in this track is limited by the parameter SegmentDuration, so multiple records are created with the same ID when a vehicle remains in the scene for longer than this duration. | Yes |
SegmentedResultWithSource
|
VehicleModelResultAndImage | (Available only when processing video). The same as the SegmentedResult track, but each record also includes the best source frame. |
No |
VehicleMakeImage
|
VehicleMakeResultAndPatch | Contains a record for each result. Each record includes a scaled image of the grille patch that was used for identifying the vehicle make. | No |
Field name | Type | Description |
---|---|---|
id | UUIDData | A universally unique identifier to identify the result. |
colorregion | PolygonData | Describes a region in the source image that is expected to contain a sample of the vehicle color. |
image | ImageData | The source image. |
colorregionpercentage | Integer | The percentage of the color region contained within the source image. It is possible for the color region to be outside the source image, for example when only part of the vehicle appears in the image. |
Field name | Type | Description |
---|---|---|
id | UUIDData | A universally unique identifier to identify the result. |
grillepatch | PolygonData | Describes the region of the image that contains the vehicle grille. |
identity | IdentityData | The identity of the vehicle in the database that matches the vehicle in the image. If the vehicle was not recognized, this field is empty. |
grillepercentage | Integer | The percentage of the vehicle grille that was visible in the source image. |
vehiclemake | String | The identified vehicle make. |
vehiclemakescore | Integer | A confidence score for vehicle make recognition, from 0 to 100, where 100 indicates maximum confidence. |
The same as VehicleModelResult
records, with the following additional fields.
Field name | Type | Description |
---|---|---|
image | ImageData | The source image. |
Field name | Type | Description |
---|---|---|
id | UUIDData | A universally unique identifier to identify the result. |
index | Integer | An integer to identify the region used for vehicle make recognition (Media Server can attempt vehicle make recognition on multiple regions if the first is unsuccessful). |
image | ImageData | A scaled image of the grille patch that was used to identify the vehicle make. |
vehiclemake | String | The identified vehicle make, or "unknown". |
vehiclemakescore | Integer | A confidence score for vehicle make recognition, from 0 to 100, where 100 indicates maximum confidence. |
|