Options to configure the MediaPipe PoseLandmarker Task
Signature:
export
declare
interface
PoseLandmarkerOptions
extends
VisionTaskOptions
Extends: VisionTaskOptions
Properties
| Property | Type | Description |
|---|---|---|
| number | undefined | The minimum confidence score for the pose detection to be considered successful. Defaults to 0.5. | |
| number | undefined | The minimum confidence score of pose presence score in the pose landmark detection. Defaults to 0.5. | |
| number | undefined | The minimum confidence score for the pose tracking to be considered successful. Defaults to 0.5. | |
| number | undefined | The maximum number of poses can be detected by the PoseLandmarker. Defaults to 1. | |
| boolean | undefined | Whether to output segmentation masks. Defaults to false. |
PoseLandmarkerOptions.minPoseDetectionConfidence
The minimum confidence score for the pose detection to be considered successful. Defaults to 0.5.
Signature:
minPoseDetectionConfidence?
:
number
|
undefined
;
PoseLandmarkerOptions.minPosePresenceConfidence
The minimum confidence score of pose presence score in the pose landmark detection. Defaults to 0.5.
Signature:
minPosePresenceConfidence?
:
number
|
undefined
;
PoseLandmarkerOptions.minTrackingConfidence
The minimum confidence score for the pose tracking to be considered successful. Defaults to 0.5.
Signature:
minTrackingConfidence?
:
number
|
undefined
;
PoseLandmarkerOptions.numPoses
The maximum number of poses can be detected by the PoseLandmarker. Defaults to 1.
Signature:
numPoses?
:
number
|
undefined
;
PoseLandmarkerOptions.outputSegmentationMasks
Whether to output segmentation masks. Defaults to false.
Signature:
outputSegmentationMasks?
:
boolean
|
undefined
;

