pandora2d.refinement.dichotomy_cpp

Module for Dichotomy refinement method (cpp version).

Classes

Dichotomy

Subpixel refinement method by dichotomy (cpp version).

Functions

disparity_to_index(→ numpy.ndarray)	Transform a disparity map to index map. Indexes correspond to (row/col) disparities in cost volume.
index_to_disparity(→ numpy.ndarray)	Transform an index map to disparity map. Indexes correspond to (row/col) disparities in cost volume.
create_cost_values_map(→ numpy.ndarray)	Return the map with best matching score

Module Contents

class pandora2d.refinement.dichotomy_cpp.Dichotomy(cfg: dict = None, _: list = None, __: int = 5)

Bases: pandora2d.refinement.refinement.AbstractRefinement

Subpixel refinement method by dichotomy (cpp version).

NB_MAX_ITER = 9

schema

filter

classmethod check_conf(cfg: dict) → dict

Check the refinement method configuration.

Will change number_of_iterations value by Dichotomy.NB_MAX_ITER if above Dichotomy.NB_MAX_ITER.

Parameters:

cfg – user_config for refinement method

Returns:

cfg: global configuration

property margins

Create margins for dichotomy object.

It will be used for ROI and for dichotomy window extraction from cost volumes.

refinement_method(cost_volumes: xarray.Dataset, disp_map: xarray.Dataset, img_left: xarray.Dataset, img_right: xarray.Dataset) → tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray]

Return the subpixel disparity maps

Parameters:

• cost_volumes – cost_volumes 4D row, col, disp_col, disp_row

• disp_map – pixel disparity maps

• img_left – left image dataset

• img_right – right image dataset

Returns:

the refined disparity maps

pandora2d.refinement.dichotomy_cpp.disparity_to_index(disparity_map: xarray.DataArray, shift: int, subpixel: int) → numpy.ndarray

Transform a disparity map to index map. Indexes correspond to (row/col) disparities in cost volume.

Example:

• with subpixel=1 :

  • disparity_map = -2 -1 -1 1

    -1

    0 -1 -1 0 1 1 1

  • disparities range = [-4 -3 -2 -1 0 1 2 3]

  • index_map = 2 3 3 5

    3 4 3 3 4 5 5 5

• with subpixel=2 :

  • disparity_map = -4 -2 -1.5 -2.5

    -4

    -1

    -1

    -1

    -4

    -1.5 -1 -1.5

  • disparities range = [-4 -3.5 -3 -2.5 -2 -1.5 -1]

  • index_map = 0 4 5 3

    0 6 6 6 0 5 6 5

Parameters:

• disparity_map – 2D map

• shift – the first value of the disparity coordinates in the cost volume

• subpixel – :sub-sampling of cost_volume

Returns:

the index map

pandora2d.refinement.dichotomy_cpp.index_to_disparity(index_map: numpy.ndarray, shift: int, subpixel: int) → numpy.ndarray

Transform an index map to disparity map. Indexes correspond to (row/col) disparities in cost volume.

For examples, see disparity_to_index method.

Parameters:

• index_map – 2D map

• shift – the first value of the disparity coordinates in the cost volume

• subpixel – :sub-sampling of cost_volume

Returns:

the index map

pandora2d.refinement.dichotomy_cpp.create_cost_values_map(cost_volumes: xarray.Dataset, disp_map: xarray.Dataset) → numpy.ndarray

Return the map with best matching score

Parameters:

• cost_volumes – cost_volumes 4D row, col, disp_col, disp_row

• disp_map – pixel disparity maps

Returns:

the cost_value map and the invalid_disparity_map