pandora.multiscale.multiscale

This module contains functions associated to the multiscale step.

Module Contents

Classes

AbstractMultiscale

Abstract Multiscale class

class pandora.multiscale.multiscale.AbstractMultiscale

Abstract Multiscale class

__metaclass__

multiscale_methods_avail: Dict

cfg

classmethod register_subclass(short_name: str, *args)

Allows to register the subclass with its short name

Parameters:

• short_name (string) – the subclass to be registered

• args – allows to register one plugin that contains different methods

abstract desc()

Describes the multiscale method

abstract disparity_range(disp: xarray.Dataset, disp_min: numpy.ndarray, disp_max: numpy.ndarray) → Tuple[numpy.ndarray, numpy.ndarray]

Disparity range computation by seeking the max and min values in the window. Unvalid disparities are given the full disparity range

Parameters:

• disp (xarray.Dataset with the data variables : - disparity_map 2D xarray.DataArray (row, col) - confidence_measure 3D xarray.DataArray(row, col, indicator)) – the disparity dataset

• disp_min (np.ndarray) – absolute min disparity

• disp_max (np.ndarray) – absolute max disparity

Returns:

Two np.darray : - disp_min_range : minimum disparity value for all pixels : - disp_max_range : maximum disparity value for all pixels.

Return type:

tuple (np.ndarray, np.ndarray)

static mask_invalid_disparities(disp: xarray.Dataset) → numpy.ndarray

Return a copied disparity map with all invalid disparities set to Nan

Parameters:

disp (xarray.Dataset with the data variables : - disparity_map 2D xarray.DataArray (row, col) - confidence_measure 3D xarray.DataArray(row, col, indicator)) – the disparity dataset

Returns:

np.darray : - filtered_disp_map : disparity map with invalid values set to Nzn

Return type:

tuple (np.ndarray, np.ndarray)