Detect poses with ML Kit on Android

ML Kit provides two optimized SDKs for pose detection.

Try it out

• Play around with the sample app to see an example usage of this API.

Before you begin

1. In your project-level build.gradle file, make sure to include Google's Maven repository in both your buildscript and allprojects sections.

2. Add the dependencies for the ML Kit Android libraries to your module's app-level gradle file, which is usually app/build.gradle:

   dependencies {
     // If you want to use the base sdk
     implementation 'com.google.mlkit:pose-detection:18.0.0-beta5'
     // If you want to use the accurate sdk
     implementation 'com.google.mlkit:pose-detection-accurate:18.0.0-beta5'
   }
   

1. Create an instance of PoseDetector

PoseDetector options

To detect a pose in an image, first create an instance of PoseDetector and optionally specify the detector settings.

Detection mode

The PoseDetector operates in two detection modes. Be sure you choose the one that matches your use case.

STREAM_MODE (default)

The pose detector will first detect the most prominent person in the image and then run pose detection. In subsequent frames, the person-detection step will not be conducted unless the person becomes obscured or is no longer detected with high confidence. The pose detector will attempt to track the most-prominent person and return their pose in each inference. This reduces latency and smooths detection. Use this mode when you want to detect pose in a video stream.

SINGLE_IMAGE_MODE

The pose detector will detect a person and then run pose detection. The person-detection step will run for every image, so latency will be higher, and there is no person-tracking. Use this mode when using pose detection on static images or where tracking is not desired.

Hardware config

The PoseDetector supports multiple hardware configurations for optimizing performance:

• CPU: run the detector by using CPU only
• CPU_GPU: run the detector by using both CPU and GPU

When building the detector options, you can use the API setPreferredHardwareConfigs to control the hardware selection. By default, all hardware configurations are set as preferred.

ML Kit will take availability, stability, correctness and latency of each config into consideration and pick the best one from the preferred configs. If none of the preferred configs is applicable, the CPU config will be used automatically as fallback. ML Kit will do these checks and related preparation in a non-blocking way before enabling any acceleration, so it is most likely the first time your user runs the detector, it will use CPU. After all the preparation finishes, the best config will be used in the following runs.

Example usages of setPreferredHardwareConfigs:

• To let ML Kit pick the best config, do not call this API.
• If you don't want to enable any acceleration, pass in only CPU.
• If you want to use GPU to offload CPU even if GPU could be slower, pass in only CPU_GPU.

Specify the pose detector options:

// Base pose detector with streaming frames, when depending on the pose-detection sdk
val options = PoseDetectorOptions.Builder()
    .setDetectorMode(PoseDetectorOptions.STREAM_MODE)
    .build()

// Accurate pose detector on static images, when depending on the pose-detection-accurate sdk
val options = AccuratePoseDetectorOptions.Builder()
    .setDetectorMode(AccuratePoseDetectorOptions.SINGLE_IMAGE_MODE)
    .build()

// Base pose detector with streaming frames, when depending on the pose-detection sdk
PoseDetectorOptions options =
   new PoseDetectorOptions.Builder()
       .setDetectorMode(PoseDetectorOptions.STREAM_MODE)
       .build();

// Accurate pose detector on static images, when depending on the pose-detection-accurate sdk
AccuratePoseDetectorOptions options =
   new AccuratePoseDetectorOptions.Builder()
       .setDetectorMode(AccuratePoseDetectorOptions.SINGLE_IMAGE_MODE)
       .build();

Finally, create an instance of PoseDetector. Pass the options you specified:

val poseDetector = PoseDetection.getClient(options)

PoseDetector poseDetector = PoseDetection.getClient(options);

2. Prepare the input image

To detect poses in an image, create an InputImage object from either a Bitmap, media.Image, ByteBuffer, byte array, or a file on the device. Then, pass the InputImage object to the PoseDetector.

For pose detection, you should use an image with dimensions of at least 480x360 pixels. If you are detecting poses in real time, capturing frames at this minimum resolution can help reduce latency.

You can create an InputImage object from different sources, each is explained below.

Using a media.Image

To create an InputImage object from a media.Image object, such as when you capture an image from a device's camera, pass the media.Image object and the image's rotation to InputImage.fromMediaImage().

If you use the CameraX library, the OnImageCapturedListener and ImageAnalysis.Analyzer classes calculate the rotation value for you.

private class YourImageAnalyzer : ImageAnalysis.Analyzer {

    override fun analyze(imageProxy: ImageProxy) {
        val mediaImage = imageProxy.image
        if (mediaImage != null) {
            val image = InputImage.fromMediaImage(mediaImage, imageProxy.imageInfo.rotationDegrees)
            // Pass image to an ML Kit Vision API
            // ...
        }
    }
}

private class YourAnalyzer implements ImageAnalysis.Analyzer {

    @Override
    public void analyze(ImageProxy imageProxy) {
        Image mediaImage = imageProxy.getImage();
        if (mediaImage != null) {
          InputImage image =
                InputImage.fromMediaImage(mediaImage, imageProxy.getImageInfo().getRotationDegrees());
          // Pass image to an ML Kit Vision API
          // ...
        }
    }
}

If you don't use a camera library that gives you the image's rotation degree, you can calculate it from the device's rotation degree and the orientation of camera sensor in the device:

private val ORIENTATIONS = SparseIntArray()

init {
    ORIENTATIONS.append(Surface.ROTATION_0, 0)
    ORIENTATIONS.append(Surface.ROTATION_90, 90)
    ORIENTATIONS.append(Surface.ROTATION_180, 180)
    ORIENTATIONS.append(Surface.ROTATION_270, 270)
}

/**
 * Get the angle by which an image must be rotated given the device's current
 * orientation.
 */
@RequiresApi(api = Build.VERSION_CODES.LOLLIPOP)
@Throws(CameraAccessException::class)
private fun getRotationCompensation(cameraId: String, activity: Activity, isFrontFacing: Boolean): Int {
    // Get the device's current rotation relative to its "native" orientation.
    // Then, from the ORIENTATIONS table, look up the angle the image must be
    // rotated to compensate for the device's rotation.
    val deviceRotation = activity.windowManager.defaultDisplay.rotation
    var rotationCompensation = ORIENTATIONS.get(deviceRotation)

    // Get the device's sensor orientation.
    val cameraManager = activity.getSystemService(CAMERA_SERVICE) as CameraManager
    val sensorOrientation = cameraManager
            .getCameraCharacteristics(cameraId)
            .get(CameraCharacteristics.SENSOR_ORIENTATION)!!

    if (isFrontFacing) {
        rotationCompensation = (sensorOrientation + rotationCompensation) % 360
    } else { // back-facing
        rotationCompensation = (sensorOrientation - rotationCompensation + 360) % 360
    }
    return rotationCompensation
}
MLKitVisionImage.kt

private static final SparseIntArray ORIENTATIONS = new SparseIntArray();
static {
    ORIENTATIONS.append(Surface.ROTATION_0, 0);
    ORIENTATIONS.append(Surface.ROTATION_90, 90);
    ORIENTATIONS.append(Surface.ROTATION_180, 180);
    ORIENTATIONS.append(Surface.ROTATION_270, 270);
}

/**
 * Get the angle by which an image must be rotated given the device's current
 * orientation.
 */
@RequiresApi(api = Build.VERSION_CODES.LOLLIPOP)
private int getRotationCompensation(String cameraId, Activity activity, boolean isFrontFacing)
        throws CameraAccessException {
    // Get the device's current rotation relative to its "native" orientation.
    // Then, from the ORIENTATIONS table, look up the angle the image must be
    // rotated to compensate for the device's rotation.
    int deviceRotation = activity.getWindowManager().getDefaultDisplay().getRotation();
    int rotationCompensation = ORIENTATIONS.get(deviceRotation);

    // Get the device's sensor orientation.
    CameraManager cameraManager = (CameraManager) activity.getSystemService(CAMERA_SERVICE);
    int sensorOrientation = cameraManager
            .getCameraCharacteristics(cameraId)
            .get(CameraCharacteristics.SENSOR_ORIENTATION);

    if (isFrontFacing) {
        rotationCompensation = (sensorOrientation + rotationCompensation) % 360;
    } else { // back-facing
        rotationCompensation = (sensorOrientation - rotationCompensation + 360) % 360;
    }
    return rotationCompensation;
}

Then, pass the media.Image object and the rotation degree value to InputImage.fromMediaImage():

val image = InputImage.fromMediaImage(mediaImage, rotation)
MLKitVisionImage.kt

InputImage image = InputImage.fromMediaImage(mediaImage, rotation);

Using a file URI

To create an InputImage object from a file URI, pass the app context and file URI to InputImage.fromFilePath(). This is useful when you use an ACTION_GET_CONTENT intent to prompt the user to select an image from their gallery app.

val image: InputImage
try {
    image = InputImage.fromFilePath(context, uri)
} catch (e: IOException) {
    e.printStackTrace()
}
MLKitVisionImage.kt

InputImage image;
try {
    image = InputImage.fromFilePath(context, uri);
} catch (IOException e) {
    e.printStackTrace();
}

Using a ByteBuffer or ByteArray

To create an InputImage object from a ByteBuffer or a ByteArray, first calculate the image rotation degree as previously described for media.Image input. Then, create the InputImage object with the buffer or array, together with image's height, width, color encoding format, and rotation degree:

val image = InputImage.fromByteBuffer(
        byteBuffer,
        /* image width */ 480,
        /* image height */ 360,
        rotationDegrees,
        InputImage.IMAGE_FORMAT_NV21 // or IMAGE_FORMAT_YV12
)
MLKitVisionImage.kt
// Or:
val image = InputImage.fromByteArray(
        byteArray,
        /* image width */ 480,
        /* image height */ 360,
        rotationDegrees,
        InputImage.IMAGE_FORMAT_NV21 // or IMAGE_FORMAT_YV12
)
MLKitVisionImage.kt

InputImage image = InputImage.fromByteBuffer(byteBuffer,
        /* image width */ 480,
        /* image height */ 360,
        rotationDegrees,
        InputImage.IMAGE_FORMAT_NV21 // or IMAGE_FORMAT_YV12
);
MLKitVisionImage.java
// Or:
InputImage image = InputImage.fromByteArray(
        byteArray,
        /* image width */480,
        /* image height */360,
        rotation,
        InputImage.IMAGE_FORMAT_NV21 // or IMAGE_FORMAT_YV12
);
MLKitVisionImage.java

Using a Bitmap

To create an InputImage object from a Bitmap object, make the following declaration:

val image = InputImage.fromBitmap(bitmap, 0)
MLKitVisionImage.kt

InputImage image = InputImage.fromBitmap(bitmap, rotationDegree);
MLKitVisionImage.java

The image is represented by a Bitmap object together with rotation degrees.

3. Process the image

Pass the prepared InputImage object to the PoseDetector's process method.

Task<Pose> result = poseDetector.process(image)
       .addOnSuccessListener { results ->
           // Task completed successfully
           // ...
       }
       .addOnFailureListener { e ->
           // Task failed with an exception
           // ...
       }

Task<Pose> result =
        poseDetector.process(image)
                .addOnSuccessListener(
                        new OnSuccessListener<Pose>() {
                            @Override
                            public void onSuccess(Pose pose) {
                                // Task completed successfully
                                // ...
                            }
                        })
                .addOnFailureListener(
                        new OnFailureListener() {
                            @Override
                            public void onFailure(@NonNull Exception e) {
                                // Task failed with an exception
                                // ...
                            }
                        });

4. Get information about the detected pose

If a person is detected in the image, the pose detection API returns a Pose object with 33 PoseLandmarks.

If the person was not completely inside the image, the model assigns the missing landmarks coordinates outside the frame and gives them low InFrameConfidence values.

If no person was detected in the frame the Pose object contains no PoseLandmarks.

// Get all PoseLandmarks. If no person was detected, the list will be empty
val allPoseLandmarks = pose.getAllPoseLandmarks()

// Or get specific PoseLandmarks individually. These will all be null if no person
// was detected
val leftShoulder = pose.getPoseLandmark(PoseLandmark.LEFT_SHOULDER)
val rightShoulder = pose.getPoseLandmark(PoseLandmark.RIGHT_SHOULDER)
val leftElbow = pose.getPoseLandmark(PoseLandmark.LEFT_ELBOW)
val rightElbow = pose.getPoseLandmark(PoseLandmark.RIGHT_ELBOW)
val leftWrist = pose.getPoseLandmark(PoseLandmark.LEFT_WRIST)
val rightWrist = pose.getPoseLandmark(PoseLandmark.RIGHT_WRIST)
val leftHip = pose.getPoseLandmark(PoseLandmark.LEFT_HIP)
val rightHip = pose.getPoseLandmark(PoseLandmark.RIGHT_HIP)
val leftKnee = pose.getPoseLandmark(PoseLandmark.LEFT_KNEE)
val rightKnee = pose.getPoseLandmark(PoseLandmark.RIGHT_KNEE)
val leftAnkle = pose.getPoseLandmark(PoseLandmark.LEFT_ANKLE)
val rightAnkle = pose.getPoseLandmark(PoseLandmark.RIGHT_ANKLE)
val leftPinky = pose.getPoseLandmark(PoseLandmark.LEFT_PINKY)
val rightPinky = pose.getPoseLandmark(PoseLandmark.RIGHT_PINKY)
val leftIndex = pose.getPoseLandmark(PoseLandmark.LEFT_INDEX)
val rightIndex = pose.getPoseLandmark(PoseLandmark.RIGHT_INDEX)
val leftThumb = pose.getPoseLandmark(PoseLandmark.LEFT_THUMB)
val rightThumb = pose.getPoseLandmark(PoseLandmark.RIGHT_THUMB)
val leftHeel = pose.getPoseLandmark(PoseLandmark.LEFT_HEEL)
val rightHeel = pose.getPoseLandmark(PoseLandmark.RIGHT_HEEL)
val leftFootIndex = pose.getPoseLandmark(PoseLandmark.LEFT_FOOT_INDEX)
val rightFootIndex = pose.getPoseLandmark(PoseLandmark.RIGHT_FOOT_INDEX)
val nose = pose.getPoseLandmark(PoseLandmark.NOSE)
val leftEyeInner = pose.getPoseLandmark(PoseLandmark.LEFT_EYE_INNER)
val leftEye = pose.getPoseLandmark(PoseLandmark.LEFT_EYE)
val leftEyeOuter = pose.getPoseLandmark(PoseLandmark.LEFT_EYE_OUTER)
val rightEyeInner = pose.getPoseLandmark(PoseLandmark.RIGHT_EYE_INNER)
val rightEye = pose.getPoseLandmark(PoseLandmark.RIGHT_EYE)
val rightEyeOuter = pose.getPoseLandmark(PoseLandmark.RIGHT_EYE_OUTER)
val leftEar = pose.getPoseLandmark(PoseLandmark.LEFT_EAR)
val rightEar = pose.getPoseLandmark(PoseLandmark.RIGHT_EAR)
val leftMouth = pose.getPoseLandmark(PoseLandmark.LEFT_MOUTH)
val rightMouth = pose.getPoseLandmark(PoseLandmark.RIGHT_MOUTH)

// Get all PoseLandmarks. If no person was detected, the list will be empty
List<PoseLandmark> allPoseLandmarks = pose.getAllPoseLandmarks();

// Or get specific PoseLandmarks individually. These will all be null if no person
// was detected
PoseLandmark leftShoulder = pose.getPoseLandmark(PoseLandmark.LEFT_SHOULDER);
PoseLandmark rightShoulder = pose.getPoseLandmark(PoseLandmark.RIGHT_SHOULDER);
PoseLandmark leftElbow = pose.getPoseLandmark(PoseLandmark.LEFT_ELBOW);
PoseLandmark rightElbow = pose.getPoseLandmark(PoseLandmark.RIGHT_ELBOW);
PoseLandmark leftWrist = pose.getPoseLandmark(PoseLandmark.LEFT_WRIST);
PoseLandmark rightWrist = pose.getPoseLandmark(PoseLandmark.RIGHT_WRIST);
PoseLandmark leftHip = pose.getPoseLandmark(PoseLandmark.LEFT_HIP);
PoseLandmark rightHip = pose.getPoseLandmark(PoseLandmark.RIGHT_HIP);
PoseLandmark leftKnee = pose.getPoseLandmark(PoseLandmark.LEFT_KNEE);
PoseLandmark rightKnee = pose.getPoseLandmark(PoseLandmark.RIGHT_KNEE);
PoseLandmark leftAnkle = pose.getPoseLandmark(PoseLandmark.LEFT_ANKLE);
PoseLandmark rightAnkle = pose.getPoseLandmark(PoseLandmark.RIGHT_ANKLE);
PoseLandmark leftPinky = pose.getPoseLandmark(PoseLandmark.LEFT_PINKY);
PoseLandmark rightPinky = pose.getPoseLandmark(PoseLandmark.RIGHT_PINKY);
PoseLandmark leftIndex = pose.getPoseLandmark(PoseLandmark.LEFT_INDEX);
PoseLandmark rightIndex = pose.getPoseLandmark(PoseLandmark.RIGHT_INDEX);
PoseLandmark leftThumb = pose.getPoseLandmark(PoseLandmark.LEFT_THUMB);
PoseLandmark rightThumb = pose.getPoseLandmark(PoseLandmark.RIGHT_THUMB);
PoseLandmark leftHeel = pose.getPoseLandmark(PoseLandmark.LEFT_HEEL);
PoseLandmark rightHeel = pose.getPoseLandmark(PoseLandmark.RIGHT_HEEL);
PoseLandmark leftFootIndex = pose.getPoseLandmark(PoseLandmark.LEFT_FOOT_INDEX);
PoseLandmark rightFootIndex = pose.getPoseLandmark(PoseLandmark.RIGHT_FOOT_INDEX);
PoseLandmark nose = pose.getPoseLandmark(PoseLandmark.NOSE);
PoseLandmark leftEyeInner = pose.getPoseLandmark(PoseLandmark.LEFT_EYE_INNER);
PoseLandmark leftEye = pose.getPoseLandmark(PoseLandmark.LEFT_EYE);
PoseLandmark leftEyeOuter = pose.getPoseLandmark(PoseLandmark.LEFT_EYE_OUTER);
PoseLandmark rightEyeInner = pose.getPoseLandmark(PoseLandmark.RIGHT_EYE_INNER);
PoseLandmark rightEye = pose.getPoseLandmark(PoseLandmark.RIGHT_EYE);
PoseLandmark rightEyeOuter = pose.getPoseLandmark(PoseLandmark.RIGHT_EYE_OUTER);
PoseLandmark leftEar = pose.getPoseLandmark(PoseLandmark.LEFT_EAR);
PoseLandmark rightEar = pose.getPoseLandmark(PoseLandmark.RIGHT_EAR);
PoseLandmark leftMouth = pose.getPoseLandmark(PoseLandmark.LEFT_MOUTH);
PoseLandmark rightMouth = pose.getPoseLandmark(PoseLandmark.RIGHT_MOUTH);

Tips to improve performance

The quality of your results depends on the quality of the input image:

• For ML Kit to accurately detect pose, the person in the image should be represented by sufficient pixel data; for best performance, the subject should be at least 256x256 pixels.
• If you detect pose in a real-time application, you might also want to consider the overall dimensions of the input images. Smaller images can be processed faster, so to reduce latency, capture images at lower resolutions, but keep in mind the above resolution requirements and ensure that the subject occupies as much of the image as possible.
• Poor image focus can also impact accuracy. If you don't get acceptable results, ask the user to recapture the image.

If you want to use pose detection in a real-time application, follow these guidelines to achieve the best framerates:

• Use the base pose-detection sdk and STREAM_MODE.
• Consider capturing images at a lower resolution. However, also keep in mind this API's image dimension requirements.
• If you use the Camera or camera2 API, throttle calls to the detector. If a new video frame becomes available while the detector is running, drop the frame. See the VisionProcessorBase class in the quickstart sample app for an example.
• If you use the CameraX API, be sure that backpressure strategy is set to its default value ImageAnalysis.STRATEGY_KEEP_ONLY_LATEST. This guarantees only one image will be delivered for analysis at a time. If more images are produced when the analyzer is busy, they will be dropped automatically and not queued for delivery. Once the image being analyzed is closed by calling ImageProxy.close(), the next latest image will be delivered.
• If you use the output of the detector to overlay graphics on the input image, first get the result from ML Kit, then render the image and overlay in a single step. This renders to the display surface only once for each input frame. See the CameraSourcePreview and GraphicOverlay classes in the quickstart sample app for an example.
• If you use the Camera2 API, capture images in ImageFormat.YUV_420_888 format. If you use the older Camera API, capture images in ImageFormat.NV21 format.

Next steps

• To learn how to use pose landmarks to classify poses, see Pose Classification Tips.