pandora.cost_volume_confidence.ambiguity
========================================

.. py:module:: pandora.cost_volume_confidence.ambiguity

.. autoapi-nested-parse::

   This module contains functions for estimating confidence from ambiguity.



Classes
-------

.. autoapisummary::

   pandora.cost_volume_confidence.ambiguity.Ambiguity


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

.. py:class:: Ambiguity(**cfg: str)

   Bases: :py:obj:`pandora.cost_volume_confidence.cost_volume_confidence.AbstractCostVolumeConfidence`


   Ambiguity class allows to estimate a confidence from the cost volume


   .. py:attribute:: _ETA_MIN
      :value: 0.0



   .. py:attribute:: _ETA_MAX
      :value: 0.7



   .. py:attribute:: _ETA_STEP
      :value: 0.01



   .. py:attribute:: _PERCENTILE
      :value: 1.0



   .. py:attribute:: _NORMALIZATION
      :value: True



   .. py:attribute:: _method
      :value: 'ambiguity'



   .. py:attribute:: cfg


   .. py:attribute:: _eta_min
      :value: 0.0



   .. py:attribute:: _percentile
      :value: 1.0



   .. py:attribute:: _normalization


   .. py:attribute:: _eta_max


   .. py:attribute:: _eta_step


   .. py:attribute:: _indicator
      :value: 'ambiguity'



   .. py:attribute:: _etas


   .. py:attribute:: _nbr_etas


   .. py:method:: check_conf(**cfg: Union[str, float]) -> Dict[str, Union[str, float]]

      Add default values to the dictionary if there are missing elements and check if the dictionary is correct

      :param cfg: ambiguity configuration
      :type cfg: dict
      :return cfg: ambiguity configuration updated
      :rtype: dict



   .. py:method:: desc() -> None

      Describes the confidence method
      :return: None



   .. py:method:: confidence_prediction(disp: xarray.Dataset, img_left: xarray.Dataset = None, img_right: xarray.Dataset = None, cv: xarray.Dataset = None) -> Tuple[xarray.Dataset, xarray.Dataset]

      Computes a confidence measure that evaluates the matching cost function at each point

      :param disp: the disparity map dataset
      :type disp: xarray.Dataset
      :param img_left: left Dataset image
      :tye img_left: xarray.Dataset
      :param img_right: right Dataset image
      :type img_right: xarray.Dataset
      :param cv: cost volume dataset
      :type cv: xarray.Dataset
      :return: the disparity map and the cost volume with a new indicator 'ambiguity_confidence' in the DataArray
               confidence_measure
      :rtype: Tuple(xarray.Dataset, xarray.Dataset) with the data variables:

              - confidence_measure 3D xarray.DataArray (row, col, indicator)



   .. py:method:: normalize_with_percentile(ambiguity: numpy.ndarray) -> numpy.ndarray

      Normalize ambiguity with percentile .
      Cost Volume must correspond to min similarity measure

      :param ambiguity: ambiguity
      :type ambiguity: 2D np.ndarray (row, col) dtype = float32
      :return: the normalized ambiguity
      :rtype: 2D np.ndarray (row, col) dtype = float32



   .. py:method:: compute_ambiguity(cv: numpy.ndarray, etas: numpy.ndarray, nbr_etas: int, grids: numpy.ndarray, disparity_range: numpy.ndarray) -> numpy.ndarray
      :staticmethod:


      Computes ambiguity.

      :param cv: cost volume
      :type cv: 3D np.ndarray (row, col, disp)
      :param etas: range between eta_min and eta_max with step eta_step
      :type etas: np.ndarray
      :param nbr_etas: number of etas
      :type nbr_etas: int
      :param grids: array containing min and max disparity grids
      :type grids: 2D np.ndarray (min, max)
      :param disparity_range: array containing disparity range
      :type disparity_range: np.ndarray
      :return: the normalized ambiguity
      :rtype: 2D np.ndarray (row, col) dtype = float32



   .. py:method:: compute_ambiguity_and_sampled_ambiguity(cv: numpy.ndarray, etas: numpy.ndarray, nbr_etas: int, grids: numpy.ndarray, disparity_range: numpy.ndarray)
      :staticmethod:


      Return the ambiguity and sampled ambiguity, useful for evaluating ambiguity in notebooks

      :param cv: cost volume
      :type cv: 3D np.ndarray (row, col, disp)
      :param etas: range between eta_min and eta_max with step eta_step
      :type etas: np.ndarray
      :param nbr_etas: nuber of etas
      :type nbr_etas: int
      :param grids: array containing min and max disparity grids
      :type grids: 2D np.ndarray (min, max)
      :param disparity_range: array containing disparity range
      :type disparity_range: np.ndarray
      :return: the normalized ambiguity and sampled ambiguity
      :rtype: Tuple(2D np.ndarray (row, col) dtype = float32, 3D np.ndarray (row, col) dtype = float32)