robokudo.annotators.tsdf_annotator
==================================

.. py:module:: robokudo.annotators.tsdf_annotator


Classes
-------

.. autoapisummary::

   robokudo.annotators.tsdf_annotator.TSDFAnnotatorVisualizationModes
   robokudo.annotators.tsdf_annotator.TSDFAnnotator


Module Contents
---------------

.. py:class:: TSDFAnnotatorVisualizationModes

   Bases: :py:obj:`enum.Enum`


   Enumeration of supported visualization modes for TSDF volumes.


   .. py:attribute:: NONE
      :value: 'none'



   .. py:attribute:: MESH
      :value: 'mesh'



   .. py:attribute:: POINTCLOUD
      :value: 'pointcloud'



   .. py:attribute:: VOXEL_POINTCLOUD
      :value: 'voxel_pointcloud'



.. py:class:: TSDFAnnotator(name: str = 'TSDFAnnotator', descriptor: TSDFAnnotator = Descriptor())

   Bases: :py:obj:`robokudo.annotators.core.ThreadedAnnotator`


   Annotator for per-object TSDF volume integration.

   .. note::
       The annotator requires a camera to world transform and object poses to integrate the TSDF volumes.
       To segment objects out of the image a mask is required too. Higher quality masks yield better results.


   .. py:class:: Descriptor

      Bases: :py:obj:`robokudo.annotators.core.BaseAnnotator.Descriptor`


      Configuration descriptor for the TSDF annotator.


      .. py:class:: Parameters

         Bases: :py:obj:`robokudo.annotators.core.BaseAnnotator.Descriptor.Parameters`


         Parameters for configuring the TSDF annotator.


         .. py:attribute:: voxel_length
            :type:  float
            :value: 0.005


            Voxel length for the TSDF volume of each object.



         .. py:attribute:: sdf_trunc
            :type:  float
            :value: 0.04


            SDF truncation distance for the TSDF volume of each object.



         .. py:attribute:: depth_scale
            :type:  float
            :value: 1000.0


            Depth scale for the TSDF volume integration.



         .. py:attribute:: depth_trunc
            :type:  float
            :value: 3.0


            Depth truncation distance for the TSDF volume integration.



         .. py:attribute:: geometry_visualization_mode
            :type:  TSDFAnnotatorVisualizationModes

            Whether to visualize the TSDF as a mesh or a point cloud. 




      .. py:attribute:: parameters



   .. py:attribute:: translation_comparator

      Translation comparator for comparing world positions between pipeline iterations.



   .. py:attribute:: tracked_objects
      :type:  typing_extensions.List[typing_extensions.Dict[str, typing_extensions.Any]]
      :value: []


      A list of tracked object data, including the bounding box and the TSDF volume.



   .. py:method:: find_tracked_object(pose: robokudo.types.annotation.PoseAnnotation, threshold: float = 0.75) -> typing_extensions.Optional[typing_extensions.Dict[str, typing_extensions.Any]]

      Check whether the given bounding box is similar to one that has been seen before.

      :param pose: The pose to check
      :param threshold: The similarity threshold between 0.0 and 1.0 for considering the bounding box similar.
      :return: The most similar tracked object or none if no similar object was found.



   .. py:method:: compute() -> py_trees.common.Status

      Generate a TSDF volume for each object hypothesis or integrate into existing volumes.

      :return: Whether the TSDF integration was successful or not.



   .. py:method:: get_visualization_image(image: numpy.typing.NDArray[numpy.uint8], oh_data: typing_extensions.List[typing_extensions.Tuple[robokudo.types.scene.ObjectHypothesis, robokudo.types.annotation.PoseAnnotation, typing_extensions.Tuple[int, int, int, int]]], masks: typing_extensions.List[numpy.typing.NDArray[numpy.uint8]]) -> numpy.typing.NDArray[numpy.uint8]

      Get an image containing the bounding boxes and masks of objects.

      :param image: The image to add the visualizations to.
      :param oh_data: The object hypotheses to visualize.
      :param masks: The masks to visualize.
      :return: The image with the visualizations.



   .. py:method:: get_visualization_geometries(volume: robokudo.types.cv.TSDFAnnotation) -> typing_extensions.List[open3d.geometry.Geometry]

      Get visualization geometries for the TSDF volume depending on the visualization mode.

      :param volume: The TSDF volume annotation to visualize.
      :return: List of visualization geometries for the given volume annotation.