cars.applications.dense_matching.dense_matching_algo
====================================================

.. py:module:: cars.applications.dense_matching.dense_matching_algo

.. autoapi-nested-parse::

   This module is responsible for the dense matching algorithms:
   - thus it creates a disparity map from a pair of images



Classes
-------

.. autoapisummary::

   cars.applications.dense_matching.dense_matching_algo.LinearInterpNearestExtrap


Functions
---------

.. autoapisummary::

   cars.applications.dense_matching.dense_matching_algo.compute_disparity_grid
   cars.applications.dense_matching.dense_matching_algo.compute_disparity


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

.. py:function:: compute_disparity_grid(disp_range_grid, left_image_object, right_image_object, used_band, threshold_disp_range_to_borders)

   Compute dense disparity grids min and max for pandora
   superposable to left image

   :param disp_range_grid: disp range grid with min and max grids
   :type disp_range_grid: CarsDataset
   :param left_image_object: left image
   :type left_image_object: xr.Dataset

   :return disp min map, disp_max_map
   :rtype np.ndarray, np.ndarray


.. py:function:: compute_disparity(left_dataset, right_dataset, corr_cfg, used_band=None, disp_min_grid=None, disp_max_grid=None, compute_disparity_masks=False, cropped_range=None, margins_to_keep=0, classification_fusion_margin=-1, texture_bands=None, filter_incomplete_disparity_range=True, classif_bands_to_mask=None) -> Dict[str, xarray.Dataset]

   This function will compute disparity.

   :param left_dataset: Dataset containing left image and mask
   :type left_dataset: xarray.Dataset
   :param right_dataset: Dataset containing right image and mask
   :type right_dataset: xarray.Dataset
   :param corr_cfg: Correlator configuration
   :type corr_cfg: dict
   :param used_band: name of band used for correlation
   :type used_band: str
   :param disp_min_grid: Minimum disparity grid
                    (if None, value is taken from left dataset)
   :type disp_min_grid: np ndarray
   :param disp_max_grid: Maximum disparity grid
                    (if None, value is taken from left dataset)
   :type disp_max_grid: np ndarray
   :param compute_disparity_masks: Activation of compute_disparity_masks mode
   :type compute_disparity_masks: Boolean
   :param cropped_range: true if disparity range was cropped
   :type cropped_range: numpy array
   :param margins_to_keep: margin to keep after dense matching
   :type margins_to_keep: int
   :param classification_fusion_margin: the margin to add for the fusion
   :type classification_fusion_margin: int
   :param classif_bands_to_mask: bands from classif to mask
   :type classif_bands_to_mask: list of str / int


   :return: Disparity dataset


.. py:class:: LinearInterpNearestExtrap(points, values)

   Linear interpolation and nearest neighbour extrapolation


   .. py:attribute:: interp


   .. py:attribute:: extrap


   .. py:method:: __call__(*args)