cars.applications.dense_match_filling.abstract_dense_match_filling_app

this module contains the abstract dense matches filling application class.

Classes

DenseMatchFilling

DenseMatchFilling

Module Contents

class cars.applications.dense_match_filling.abstract_dense_match_filling_app.DenseMatchFilling(conf=None)

Bases: cars.applications.application_template.ApplicationTemplate

DenseMatchFilling

available_applications: Dict

default_application = 'zero_padding'

classmethod __init_subclass__(short_name, **kwargs)

abstract get_poly_margin()

Get the margin used for polygon

Returns:

self.nb_pix

Return type:

int

get_classif()

Get classification band list :return: self.classification :rtype: list[str]

abstract run(epipolar_disparity_map, **kwargs)

Run filling application.

Parameters:

epipolar_disparity_map (CarsDataset) – left disparity

Returns:

filled disparity map: The CarsDataset contains:

• N x M Delayed tiles. Each tile will be a future xarray Dataset containing:

  • data with keys : “disp”, “disp_msk”

  • attrs with keys: profile, window, overlaps

• attributes containing:

  ”largest_epipolar_region”,”opt_epipolar_tile_size”,

  ”epipolar_regions_grid”

Return type:

CarsDataset

__register_dataset__(epipolar_disparity_map, save_intermediate_data, pair_folder, pair_key, app_name=None, nodata_epi_disp=0)

Create dataset and registered the output in the orchestrator

Parameters:

• epipolar_disparity_map (CarsDataset) – left disparity

• save_intermediate_data (bool) – true to save disparity map

• pair_folder (str) – path to folder

• pair_key (str) – pair id

• app_name (str) – application name for file names

• nodata_epi_disp (int) – the nodata for the epi disp