nicetoolbox.detectors.method_detectors.mmpose.mmpose_framework_2d.MMPose2D

class nicetoolbox.detectors.method_detectors.mmpose.mmpose_framework_2d.MMPose2D(io: SequenceIO, data: SequenceData, sequence_context: SequenceRuntimeConfig, algorithm_instance: str)

Bases: BaseMMPose

The MMPose2D class is a method detector for 2D pose estimation using the MMPose framework.

Its post_inference method computes 3D points via multi-view stereo triangulation. components is set per-instance from the TOML config (e.g. body-only models declare components = [“body_joints”], wholebody models declare [“body_joints”, “hand_joints”, “face_landmarks”]).

Initialize base method detector with references.

Methods

compute_output_folders	Compute extra output folders for all components.
compute_result_folders	Compute result folders for all components.
compute_viz_folders	Compute visualization folders for all components.
get_per_component_keypoint_mapping	Build per-component keypoint index/description maps based on the components this instance was configured to produce.
post_inference	Post-inference processing for pose estimation components such as body_joints, hand_joints, and face_landmarks.
run	Execute method detector: run subprocess inference + post_inference.
visualization	Generates a visualization video for each camera from the processed image frames.

Attributes

algorithm_type
inference_package_name
predictions_mapping	Access predictions mapping from runtime config.
runtime
os_type
conda_path
venv
env_name
script_path
visualize
requires_out_folder
out_folders
result_folders
viz_folders
config_paths
data
io
sequence_context
detector_config
algorithm_instance
inference_config
components

compute_output_folders(requires_out_folder: bool) → Dict[str, str]

Compute extra output folders for all components.

compute_result_folders() → Dict[str, str]

Compute result folders for all components.

compute_viz_folders(visualize: bool) → Dict[str, str]

Compute visualization folders for all components.

get_per_component_keypoint_mapping(keypoints_indices)

Build per-component keypoint index/description maps based on the components this instance was configured to produce.

• body_joints: when components include hand_joints or face_landmarks we treat the model as wholebody and union body + foot keypoints; otherwise we use the body block only.

• hand_joints / face_landmarks: straightforward 1:1 mapping.

post_inference()

Post-inference processing for pose estimation components such as body_joints, hand_joints, and face_landmarks.

See module docstring for the full description of steps and outputs.

property predictions_mapping

Access predictions mapping from runtime config.

run() → None

Execute method detector: run subprocess inference + post_inference.

Returns None - visualization uses external data.

visualization(data)

Generates a visualization video for each camera from the processed image frames.

This method takes the processed image frames for each camera and compiles them into a video file. It uses the frames_to_video() function from utils.video.py. The success of the video creation is tracked, and the method logs the outcome of the visualization process for each camera. :param data: An instance of a class that stores all data related

information, including the frame rate (fps) for the video and the starting frame number (video_start).

Note

• The method assumes that the processed image frames are named in a

specific format (%09d.jpg), where each frame’s name is a zero-padded five-digit number representing its sequence in the video.