The running mode of the task. Default to the image mode.
PoseLandmarker has three running modes: 1) The image mode for detecting
pose landmarks on single image inputs. 2) The video mode for detecting
pose landmarks on the decoded frames of a video. 3) The live stream mode
for detecting pose 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_poses
The maximum number of poses can be detected by the
PoseLandmarker.
min_pose_detection_confidence
The minimum confidence score for the pose
detection to be considered successful.
min_pose_presence_confidence
The minimum confidence score of pose presence
score in the pose landmark detection.
min_tracking_confidence
The minimum confidence score for the pose tracking
to be considered successful.
output_segmentation_masks
whether to output segmentation masks.
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.