An ObjectClass analysis task recognizes the object class that the image belongs to. Before using the ObjectClass engine, you must populate the database with training images. For instructions, refer to the Media Server Administration Guide. This section describes the parameters that you can set in the configuration section for an ObjectClass task.
Configuration Parameter | Description |
---|---|
Classifier | The classifier to use for classification. |
FrameRate | The number of frames to analyze per second of video. |
Input | The image track to process. |
NumParallel | The maximum number of threads to use for running the object classification task. |
Priors | The probabilities that object classes will be seen in video. |
Region | A region of the frame to restrict processing to. |
RegionUnit | The units that the Region parameter uses to specify the size and position of a region. |
Type | The analysis engine to use. Set this parameter to ObjectClass . |
Output track | Type | Description |
---|---|---|
Result
|
ObjectClassResult | Contains a record for each object class that is detected in the video. |
ResultWithSource
|
ObjectClassResultAndImage | Contains the same information as the Result track, but each record also includes the best source frame. |
Field name | Type | Description |
---|---|---|
identifier | string | The name of the object class that matches the detected object. |
confidence | float | The confidence score for the match. |
Field name | Type | Description |
---|---|---|
identifier | string | The name of the object class that matches the detected object. |
confidence | float | The confidence score for the match. |
image | ImageData | The source frame |
|