mp.tasks.vision.HandLandmarker

Class that performs hand landmarks detection on images.

mp.tasks.vision.HandLandmarker(
    lib: mp.tasks.vision.drawing_styles.face_landmarker.serial_dispatcher.SerialDispatcher,
    handle: ctypes.c_void_p,
    dispatcher: mp.tasks.vision.drawing_styles.face_landmarker.async_result_dispatcher.AsyncResultDispatcher,
    async_callback: _C_TYPES_RESULT_CALLBACK
)

lib The dispatch library to use for the hand landmarker.
handle The C pointer to the hand landmarker.
dispatcher The async result handler for the hand landmarker.
async_callback The c callback for the hand landmarker.

Methods

close

View source

close()

Shuts down the MediaPipe task instance.

create_from_model_path

View source

@classmethod
create_from_model_path(
    model_path: str
) -> 'HandLandmarker'

Creates an HandLandmarker object from a TensorFlow Lite model and the default HandLandmarkerOptions.

Note that the created HandLandmarker instance is in image mode, for detecting hand landmarks on single image inputs.

Args
model_path Path to the model.

Returns
HandLandmarker object that's created from the model file and the default HandLandmarkerOptions.

Raises
ValueError If failed to create HandLandmarker object from the provided file such as invalid file path.
RuntimeError If other types of error occurred.

create_from_options

View source

@classmethod
create_from_options(
    options: mp.tasks.vision.HandLandmarkerOptions
) -> 'HandLandmarker'

Creates the HandLandmarker object from hand landmarker options.

Args
options Options for the hand landmarker task.

Returns
HandLandmarker object that's created from options.

Raises
ValueError If failed to create HandLandmarker object from HandLandmarkerOptions such as missing the model.
RuntimeError If other types of error occurred.

detect

View source

detect(
    image: mp.Image,
    image_processing_options: Optional[mp.tasks.vision.ImageProcessingOptions] = None
) -> mp.tasks.vision.HandLandmarkerResult

Performs hand landmarks detection on the given image.

Only use this method when the HandLandmarker is created with the image running mode.

The image can be of any size with format RGB or RGBA.

support is implemented.

Args
image MediaPipe Image.
image_processing_options Options for image processing.

Returns
The hand landmarks detection results.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If hand landmarker detection failed to run.

detect_async

View source

detect_async(
    image: mp.Image,
    timestamp_ms: int,
    image_processing_options: Optional[mp.tasks.vision.ImageProcessingOptions] = None
) -> None

Sends live image data to perform hand landmarks detection.

The results will be available via the "result_callback" provided in the HandLandmarkerOptions. Only use this method when the HandLandmarker is created with the live stream running mode.

Only use this method when the HandLandmarker is created with the live stream running mode. The input timestamps should be monotonically increasing for adjacent calls of this method. This method will return immediately after the input image is accepted. The results will be available via the result_callback provided in the HandLandmarkerOptions. The detect_async method is designed to process live stream data such as camera input. To lower the overall latency, hand landmarker may drop the input images if needed. In other words, it's not guaranteed to have output per input image.

The result_callback provides:

  • The hand landmarks detection results.
  • The input image that the hand landmarker runs on.
  • The input timestamp in milliseconds.

Args
image MediaPipe Image.
timestamp_ms The timestamp of the input image in milliseconds.
image_processing_options Options for image processing.

Raises
ValueError If the current input timestamp is smaller than what the hand landmarker has already processed.
RuntimeError If hand landmarker detection failed to initialize.

detect_for_video

View source

detect_for_video(
    image: mp.Image,
    timestamp_ms: int,
    image_processing_options: Optional[mp.tasks.vision.ImageProcessingOptions] = None
) -> mp.tasks.vision.HandLandmarkerResult

Performs hand landmarks detection on the provided video frame.

Only use this method when the HandLandmarker is created with the video running mode.

Only use this method when the HandLandmarker is created with the video running mode. It's required to provide the video frame's timestamp (in milliseconds) along with the video frame. The input timestamps should be monotonically increasing for adjacent calls of this method.

Args
image MediaPipe Image.
timestamp_ms The timestamp of the input video frame in milliseconds.
image_processing_options Options for image processing.

Returns
The hand landmarks detection results.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If hand landmarker detection failed to run.

__enter__

View source

__enter__()

Returns self upon entering the runtime context.

__exit__

View source

__exit__(
    exc_type, exc_value, traceback
)

Shuts down the MediaPipe task instance on exit of the context manager.

Args
exc_type The exception type that caused the exit.
exc_value The exception value that caused the exit.
traceback The exception traceback that caused the exit.

Raises
RuntimeError If the MediaPipe HandLandmarker task failed to close.