Appery Pose Detection

Pose detection

Present camera view with pose detection overlay

`PoseDetector.detectPoseFromCamera`

Opens the camera view with an overlay displaying detected pose landmarks. Returns the list of detected poses (for all captured frames).

Parameters

{function} success - callback function which takes a parameter data which will be invoked on success
{function} error - callback function which takes a parameter err which will be invoked on failure

Supported Options

property	value	description
detectionMode	STREAM_MODE (default) / SINGLE_IMAGE_MODE	In STREAM_MODE (default), the object detector runs with low latency, but might produce incomplete results (such as unspecified bounding boxes or category labels) on the first few invocations of the detector. Also, in STREAM_MODE, the detector assigns tracking IDs to objects, which you can use to track objects across frames. Use this mode when you want to track objects, or when low latency is important, such as when processing video streams in real time.
showDetectedPose	false / true (default)	Whether or not show silhouette of detected pose

Example

ApperyioMLCordovaPlugin.PoseDetector.detectPoseFromCamera(
    results => console.log(results),
    error => console.log(error), 
    {
        detectionMode: ApperyioMLCordovaPlugin.PoseDetector.PoseDetectorOptions.DetectionMode.STREAM,
        showDetectedPose: true
    }
);

Sample JSON callback: pose_detection.json

Present camera view with real time pose detection overlay

`PoseDetector.startRealTimeDetection`

Opens the camera view with an overlay displaying detected pose landmarks. Returns steam of detected poses.

Parameters

{function} success - callback function which takes a parameter data which will be invoked on success
{function} error - callback function which takes a parameter err which will be invoked on failure

Supported Options

property	value	description
detectionMode	STREAM_MODE (default) / SINGLE_IMAGE_MODE	In STREAM_MODE (default), the object detector runs with low latency, but might produce incomplete results (such as unspecified bounding boxes or category labels) on the first few invocations of the detector. Also, in STREAM_MODE, the detector assigns tracking IDs to objects, which you can use to track objects across frames. Use this mode when you want to track objects, or when low latency is important, such as when processing video streams in real time.
showDetectedPose	false / true (default)	Whether or not show silhouette of detected pose
frameImageData	true (default) / false	Whether include base64 of captured photo or not
frameImageResultType	CameraResultType.BASE64_STRING (default) / CameraResultType.DATA_URL	include captured photo as only base64 string or as full data url
delay	500 (default)	Time interval in msec, for performing detection each interval value
encodingType	EncodingType.JPEG (default) / EncodingType.PNG	format of output photo base64
cameraDirection	CameraDirection.BACK (default) / CameraDirection.FRONT	Use back or front camera of device during pose detection

Example

ApperyioMLCordovaPlugin.PoseDetector.startRealTimeDetection(
    results => console.log(results),
    error => console.log(error), 
    {
        detectionMode: ApperyioMLCordovaPlugin.PoseDetectorOptions.DetectionMode.STREAM,
        showDetectedPose: true,
        frameImageData: true,
        frameImageResultType: CameraResultType.DATA_URL,
        delay: 200,
        encodingType: ApperyioMLCordovaPlugin.PoseDetectorOptions.EncodingType.PNG,
        cameraDirection: ApperyioMLCordovaPlugin.PoseDetectorOptions.CameraDirection.BACK
    }
);

Sample JSON callback: pose_detection_realtime.json

Detect pose on a single image

`PoseDetector.detectPose`

Detects pose in a single image.

Parameters

{string} imageUrlOrContent - path to an image or base64 encoded image data (depending on useBase64 option)
{function} success - callback function which takes a parameter data which will be invoked on success
{function} error - callback function which takes a parameter err which will be invoked on failure

Supported Options

property	value	description
useBase64	false (default) / true	Whether or not `imageUrlOrContent` is a base64 encoded string.
detectionMode	STREAM_MODE (default) / SINGLE_IMAGE_MODE	In STREAM_MODE (default), the object detector runs with low latency, but might produce incomplete results (such as unspecified bounding boxes or category labels) on the first few invocations of the detector. Also, in STREAM_MODE, the detector assigns tracking IDs to objects, which you can use to track objects across frames. Use this mode when you want to track objects, or when low latency is important, such as when processing video streams in real time.

Example

let path = cordova.file.applicationDirectory + "image.jpg";
ApperyioMLCordovaPlugin.PoseDetector.detectPose(
    path,
    results => console.log(results),
    error => console.log(error), 
    {
        useBase64: false,
        detectionMode: ApperyioMLCordovaPlugin.PoseDetector.PoseDetectorOptions.DetectionMode.STREAM
    }
);

Sample JSON callback: pose_detection.json