pandora.interval_tools
======================

.. py:module:: pandora.interval_tools

.. autoapi-nested-parse::

   This module contains functions associated to confidence intervals.



Attributes
----------

.. autoapisummary::

   pandora.interval_tools.create_connected_graph
   pandora.interval_tools.graph_regularization


Functions
---------

.. autoapisummary::

   pandora.interval_tools.interval_regularization


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

.. py:data:: create_connected_graph

.. py:data:: graph_regularization

.. py:function:: interval_regularization(interval_inf: numpy.ndarray, interval_sup: numpy.ndarray, ambiguity: numpy.ndarray, ambiguity_threshold: float, ambiguity_kernel_size: int, vertical_depth: int = 0, quantile_regularization: float = 1.0) -> Tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray]

   Regularize interval bounds in ambiguous zones.

   :param interval_inf: lower bound of the confidence interval
   :type cv: 2D np.ndarray (row, col)
   :param interval_sup: upper bound of the confidence interval
   :type cv: 2D np.ndarray (row, col)
   :param ambiguity: ambiguity confidence map
   :type cv: 2D np.ndarray (row, col)
   :param ambiguity_threshold: threshold used for detecting ambiguous zones
   :type ambiguity_threshold: float
   :param ambiguity_kernel_size: number of columns for the minimitive kernel applied to ambiguity
   :type ambiguity_kernel_size: int
   :param vertical_depth: The number of lines above and below to look for adjacent segment during the regularization
   :type vertical_depth: int >= 0
   :param quantile_regularization: The quantile used for selecting the disparity value in the regularization step
   :type quantile_regularization: float between 0 and 1

   :return: the regularized infimum and supremum of the set containing the true disparity
       and the mask of pixel that have been regularized
   :rtype: Tuple(2D np.array (row, col) dtype = float32,
                 2D np.array (row, col) dtype = float32,
                 2D np.array (row, col) dtype = np.bool)