cars.applications.dense_matches_filling.dense_matches_filling

this module contains the abstract dense matches filling application class.

Module Contents

Classes

DenseMatchesFilling

DenseMatchesFilling

class cars.applications.dense_matches_filling.dense_matches_filling.DenseMatchesFilling(conf=None)

Bases: cars.applications.application_template.ApplicationTemplate

DenseMatchesFilling

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 Refill application using plane method.

Parameters
  • epipolar_disparity_map (CarsDataset) – left disparity

  • holes_bbox_left (CarsDataset) – left holes

  • holes_bbox_right (CarsDataset) – right holes

  • disp_min (int) – minimum disparity

  • disp_max (int) – maximum disparity

  • orchestrator – orchestrator used

  • pair_folder (str) – folder used for current pair

  • pair_key (str) – pair id

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_disparity_map, pair_folder, pair_key, app_name=None)

Create dataset and registered the output in the orchestrator

Parameters
  • epipolar_disparity_map (CarsDataset) – left disparity

  • save_disparity_map (bool) – true if save disparity map

  • pair_folder (str) – path to folder

  • pair_key (str) – pair id

  • app_name (str) – application name for file names