pandora.matching_cost.sad_ssd

This module contains functions associated to SAD and SSD methods used in the cost volume measure step.

Module Contents

Classes

SadSsd

SadSsd class allows to compute the cost volume

class pandora.matching_cost.sad_ssd.SadSsd(**cfg: str | int)

Bases: pandora.matching_cost.matching_cost.AbstractMatchingCost

SadSsd class allows to compute the cost volume

check_conf(**cfg: Dict[str, str | int]) → Dict[str, str | int]

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

Parameters:

cfg (dict) – matching cost configuration

Return cfg:

matching cost configuration updated

Return type:

dict

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

Parameters:

• img_left (xarray.Dataset) –

  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

• img_right (xarray.Dataset) –

  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

• cost_volume (xr.Dataset) – an empty cost volume

Returns:

the cost volume dataset , with the data variables:

• cost_volume 3D xarray.DataArray (row, col, disp)

Return type:

xarray.Dataset

allocate_numpy_cost_volume(img_left: xarray.Dataset, disparity_range: numpy.ndarray | List, offset_row_col: int = 0) → numpy.ndarray

Allocate the numpy cost volume cv = (disp, col, row), for efficient memory management

Parameters:

• img_left (xarray.Dataset) –

  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

• disparity_range (np.ndarray) – disparity range

• offset_row_col (int) – offset in row and col

Returns:

the cost volume dataset , with the data variables:

• cost_volume 3D xarray.DataArray (row, col, disp)

Return type:

xarray.Dataset

ad_cost(point_p: Tuple[int, int], point_q: Tuple[int, int], img_left: xarray.Dataset, img_right: xarray.Dataset) → numpy.ndarray

Computes the absolute difference

Parameters:

• point_p (tuple) – Point interval, in the left image, over which the squared difference will be applied

• point_q (tuple) – Point interval, in the right image, over which the squared difference will be applied

• img_left – left Dataset image

• img_right – right Dataset image

Returns:

the absolute difference pixel-wise between elements in the interval

Return type:

numpy array

sd_cost(point_p: Tuple, point_q: Tuple, img_left: xarray.Dataset, img_right: xarray.Dataset) → numpy.ndarray

Computes the square difference

Parameters:

• point_p (tuple) – Point interval, in the left image, over which the squared difference will be applied

• point_q (tuple) – Point interval, in the right image, over which the squared difference will be applied

• img_left – left Dataset image

• img_right – right Dataset image

Returns:

the squared difference pixel-wise between elements in the interval

Return type:

numpy array

pixel_wise_aggregation(cost_volume: numpy.ndarray) → numpy.ndarray

Summing pixel wise matching cost over square windows

param cost_volume:

the cost volume

type cost_volume:

numpy array 3D (disp, col, row)

return:

the cost volume aggregated

rtype:

numpy array 3D ( disp, col, row)