A concrete subclass of GMVFocusingDataOutput.
This dataOutput focuses on tracking a single "prominent face", in conjunction with the associated face detector. A prominent face is defined as a face which was initially the largest, most central face when tracking began. This face will continue to be tracked as the prominent face for as long as it is visible, event when it is not the largest face. When the current prominent face is no longer present, another face will be selected as the new prominent face. This class implements GMVFocusingDataOutputDelegate, so there's no need to assign dataDelegate.
|Designated initializer. More...|
|Subclasses need to override these methods. More...|
|Clean up resources. More...|
|id< GMVOutputTrackerDelegate >||trackerDelegate|
|Post processing delegation. More...|
|id< GMVFocusingDataOutputDelegate >||dataDelegate|
|Data output delegate. More...|
|Sets the camera device position to help calculate image rotation. More...|
|The video frame preview size. More...|
|The maximum allowable frames must pass without detecting a specific feature before delegate is notified the feature is no longer available. More...|
|- (instancetype) initWithDetector:||(GMVDetector *)||NS_DESIGNATED_INITIALIZER|
detector use to run detection.
|- (void) receivedResults:||(NSArray< __kindof GMVFeature * > *)||results|
Subclasses need to override these methods.
Detected GMVFeature results.
results The full detection results.
|- (void) cleanup|
Clean up resources.
Post processing delegation.
The trackerDelegate is referenced strongly. Call
-cleanup to free up internal resources.
Data output delegate.
Sets the camera device position to help calculate image rotation.
If not provided, it will try to retrieve position info through AVCaptureConnection.
The video frame preview size.
The value is used to normalize display properties.
The maximum allowable frames must pass without detecting a specific feature before delegate is notified the feature is no longer available.
The value is default to 3.