pandora.matching_cost.zncc
==========================

.. py:module:: pandora.matching_cost.zncc

.. autoapi-nested-parse::

   This module contains functions associated to ZNCC method used in the cost volume measure step.



Classes
-------

.. autoapisummary::

   pandora.matching_cost.zncc.Zncc


Functions
---------

.. autoapisummary::

   pandora.matching_cost.zncc.apply_divide_standard


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

.. py:class:: Zncc(**cfg: Union[str, int])

   Bases: :py:obj:`pandora.matching_cost.matching_cost.AbstractMatchingCost`


   Zero mean normalized cross correlation
   Zncc class allows to compute the cost volume


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

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

      :param cfg: matching cost configuration
      :type cfg: dict
      :return cfg: matching cost configuration updated
      :rtype: dict



   .. py:method:: point_interval(img_left: xarray.Dataset, img_right: xarray.Dataset, disp: float) -> Tuple[Tuple[int, int], Tuple[int, int]]

      Update point_p and point_q values if abs(disp) > nb_col - (int(self._window_size / 2) * 2).

      :param img_left: left Dataset image containing :

              - im: 2D (row, col) or 3D (band_im, row, col) xarray.DataArray float32
              - disparity (optional): 3D (disp, row, col) xarray.DataArray float32
              - msk (optional): 2D (row, col) xarray.DataArray int16
              - classif (optional): 3D (band_classif, row, col) xarray.DataArray int16
              - segm (optional): 2D (row, col) xarray.DataArray int16
      :type img_left: xarray.Dataset
      :param img_right: right Dataset image containing :

              - im: 2D (row, col) or 3D (band_im, row, col) xarray.DataArray float32
              - disparity (optional): 3D (disp, row, col) xarray.DataArray float32
              - msk (optional): 2D (row, col) xarray.DataArray int16
              - classif (optional): 3D (band_classif, row, col) xarray.DataArray int16
              - segm (optional): 2D (row, col) xarray.DataArray int16
      :type img_right: xarray.Dataset
      :param disp: current disparity
      :type disp: float
      :return: the range of the left and right image over which the similarity measure will be applied
      :rtype: tuple



   .. py:method:: compute_cost_volume(img_left: xarray.Dataset, img_right: xarray.Dataset, cost_volume: xarray.Dataset) -> xarray.Dataset

      Computes the cost volume for a pair of images

      :param img_left: left Dataset image containing :

              - im: 2D (row, col) or 3D (band_im, row, col) xarray.DataArray float32
              - disparity (optional): 3D (disp, row, col) xarray.DataArray float32
              - msk (optional): 2D (row, col) xarray.DataArray int16
              - classif (optional): 3D (band_classif, row, col) xarray.DataArray int16
              - segm (optional): 2D (row, col) xarray.DataArray int16
      :type img_left: xarray.Dataset
      :param img_right: right Dataset image containing :

              - im: 2D (row, col) or 3D (band_im, row, col) xarray.DataArray float32
              - disparity (optional): 3D (disp, row, col) xarray.DataArray float32
              - msk (optional): 2D (row, col) xarray.DataArray int16
              - classif (optional): 3D (band_classif, row, col) xarray.DataArray int16
              - segm (optional): 2D (row, col) xarray.DataArray int16
      :type img_right: xarray.Dataset
      :param cost_volume: an empty cost volume
      :type cost_volume: xr.Dataset
      :return: the cost volume dataset , with the data variables:

              - cost_volume 3D xarray.DataArray (row, col, disp)
      :rtype: xarray.Dataset



.. py:function:: apply_divide_standard(zncc: numpy.ndarray, img_left: numpy.ndarray, img_right: List[numpy.ndarray], p_std: Tuple[int, int], q_std: Tuple[int, int], i_right: int)

   Divide by the standard deviation of the intensities of the images

   :param zncc:
   :type zncc: np.ndarray
   :param img_left: standard deviation raster of left image
   :type img_left: np.ndarray
   :param img_right: standard deviation raster list of right image (for each subpix)
   :type img_right: List[np.ndarray]
   :param p_std: point interval in the left standard deviation image
   :type p_std: Tuple[int, int]
   :param q_std: Point interval in the right standard deviation image
   :type q_std: Tuple[int, int]
   :param i_right: ith image
   :type i_right: int