robokudo.annotators.region_visualizer

Region visualization for RoboKudo.

This module provides an annotator for visualizing semantic map regions in both 3D space and ROS visualization markers. It handles coordinate transformations between different reference frames to properly display regions.

Classes

RegionVisualizer

Annotator for visualizing semantic map regions.

Module Contents

class robokudo.annotators.region_visualizer.RegionVisualizer(name='RegionVisualizer', descriptor=Descriptor())

Bases: robokudo.annotators.core.ThreadedAnnotator

Annotator for visualizing semantic map regions.

This annotator retrieves a semantic map and visualizes its regions in:

  1. The 3D Annotator output using Open3D

  2. ROS Visualization Markers

The visualizer handles coordinate transformations between world frame, camera frame, and region-specific frames to properly display regions in the correct positions.

Variables:

  • world_frame_name – Name of the world coordinate frame

  • semantic_map – Loaded semantic map instance

class Descriptor

Bases: robokudo.annotators.core.BaseAnnotator.Descriptor

Configuration descriptor for region visualization.

class Parameters

Parameters for configuring region visualization.

Variables:

  • world_frame_name – Name of the world coordinate frame, defaults to “map”

  • semantic_map_ros_package – ROS package containing semantic map, defaults to “robokudo”

  • semantic_map_name – Name of semantic map module, defaults to “semantic_map_iai_kitchen”

world_frame_name = 'map'
semantic_map_ros_package = 'robokudo'
semantic_map_name = 'semantic_map_iai_kitchen'
parameters
world_frame_name
semantic_map = None
load_semantic_map() → None

Load the semantic map from the configured ROS package.

Uses ModuleLoader to dynamically load the semantic map module.

compute()

Compute the visualization of semantic map regions.

Creates visualizations containing:

  • 3D oriented bounding boxes for each region

  • Point cloud data

  • World coordinate frame

  • ROS visualization markers (via semantic map)

Handles coordinate transformations between:

  • World frame to camera frame

  • Region-specific frames to camera frame

Returns:

SUCCESS after creating visualizations

Return type:

py_trees.common.Status

Raises:

AssertionError – If region is not a valid SemanticMapEntry