mp.tasks.vision.HandLandmarkerOptions

Options for the hand landmarker task.

mp.tasks.vision.HandLandmarkerOptions(
    base_options: mp.tasks.BaseOptions,
    running_mode: mp.tasks.vision.RunningMode = mp.tasks.vision.FaceDetectorOptions.running_mode,
    num_hands: int = 1,
    min_hand_detection_confidence: float = 0.5,
    min_hand_presence_confidence: float = 0.5,
    min_tracking_confidence: float = 0.5,
    result_callback: Optional[Callable[[HandLandmarkerResult, image_module.Image, int], None]] = None
)

base_options Base options for the hand landmarker task.
running_mode The running mode of the task. Default to the image mode. HandLandmarker has three running modes: 1) The image mode for detecting hand landmarks on single image inputs. 2) The video mode for detecting hand landmarks on the decoded frames of a video. 3) The live stream mode for detecting hand landmarks on the live stream of input data, such as from camera. In this mode, the "result_callback" below must be specified to receive the detection results asynchronously.
num_hands The maximum number of hands can be detected by the hand landmarker.
min_hand_detection_confidence The minimum confidence score for the hand detection to be considered successful.
min_hand_presence_confidence The minimum confidence score of hand presence score in the hand landmark detection.
min_tracking_confidence The minimum confidence score for the hand tracking to be considered successful.
result_callback The user-defined result callback for processing live stream data. The result callback should only be specified when the running mode is set to the live stream mode.

Methods

__eq__

__eq__(
    other
)

min_hand_detection_confidence 0.5
min_hand_presence_confidence 0.5
min_tracking_confidence 0.5
num_hands 1
result_callback None
running_mode <VisionTaskRunningMode.IMAGE: 'IMAGE'>