Interface: PoseEstimationType<K>

Defined in: types/poseEstimation.ts:111

Return type of usePoseEstimation hook.

Type Parameters

K

K extends LabelEnum

The LabelEnum representing the model's keypoint schema.

Properties

downloadProgress

downloadProgress: number

Defined in: types/poseEstimation.ts:130

Represents the download progress of the model binary as a value between 0 and 1.

---

error

error: RnExecutorchError | null

Defined in: types/poseEstimation.ts:115

Contains the error object if the model failed to load or encountered a runtime error.

---

forward()

forward: (input, options?) => Promise<PoseDetections<K>>

Defined in: types/poseEstimation.ts:138

Run pose estimation on an image.

Parameters

input

Image path/URI or PixelData

string | PixelData

options?

PoseEstimationOptions

Detection options

Returns

Promise<PoseDetections<K>>

Array of detected people, each with keypoints accessible via the keypoint enum

---

getAvailableInputSizes()

getAvailableInputSizes: () => readonly number[] | undefined

Defined in: types/poseEstimation.ts:147

Returns the available input sizes for multi-method models. Returns undefined for single-method models.

Returns

readonly number[] | undefined

---

isGenerating

isGenerating: boolean

Defined in: types/poseEstimation.ts:125

Indicates whether the model is currently processing an image.

---

isReady

isReady: boolean

Defined in: types/poseEstimation.ts:120

Indicates whether the model is loaded and ready to process images.

---

runOnFrame

runOnFrame: (frame, isFrontCamera, options?) => PoseDetections<K> | null

Defined in: types/poseEstimation.ts:152

Synchronous worklet function for real-time VisionCamera frame processing.