`cars.applications.sparse_matching.pandora_sparse_matching`

this module contains the pandora_sparse_matching application class.

Module Contents

Classes

PandoraSparseMatching

Pandora low resolution class

Functions

compute_pandora_matches_wrapper(→ Dict[str, ...)

Compute pandora matches from image objects.

class cars.applications.sparse_matching.pandora_sparse_matching.PandoraSparseMatching(conf=None)[source]

Bases: cars.applications.sparse_matching.sparse_matching.SparseMatching

Pandora low resolution class

check_conf(conf)[source]

Check configuration

Parameters: conf (dict) – configuration to check
Returns: overloaded configuration
Return type: dict

get_save_matches()[source]

Get save_matches parameter

Returns: true is save_matches activated
Return type: bool

get_disparity_margin()[source]

Get disparity margin corresponding to sparse matches

Returns: margin in percent

get_connection_val()[source]

Get connection_val : distance to use to consider that two points are connected

Returns: connection_val
Return type

get_nb_pts_threshold()[source]

Get nb_pts_threshold : number of points to use to identify small clusters to filter

Returns: nb_pts_threshold

get_minimum_nb_matches()[source]

Get minimum_nb_matches : get the minimum number of matches

Returns: minimum_nb_matches

get_matches_filter_knn()[source]

Get matches_filter_knn : number of neighboors used to measure isolation of matches

Returns: matches_filter_knn

get_matches_filter_dev_factor()[source]

Get matches_filter_dev_factor : factor of deviation in the formula to compute threshold of outliers

Returns: matches_filter_dev_factor

get_filtered_elt_pos()[source]

Get filtered_elt_pos : if filtered_elt_pos is set to True, the removed points positions in their original epipolar images are returned, otherwise it is set to None

Returns: filtered_elt_pos

get_clusters_dist_thresh()[source]

Get clusters_distance_threshold : distance to use to consider if two points clusters are far from each other or not (set to None to deactivate this level of filtering)

Returns: clusters_distance_threshold

get_strip_margin()[source]

Get strip margin corresponding to sparse matches

Returns: margin in percent

get_epipolar_error_upper_bound()[source]

Get epipolar error upper bound corresponding to sparse matches

Returns: margin

get_epipolar_error_maximum_bias()[source]

Get epipolar error maximum bias corresponding to sparse matches

Returns: margin

run(epipolar_image_left, epipolar_image_right, orchestrator=None, pair_folder=None, pair_key='PAIR_0', disp_to_alt_ratio=None)[source]

Run PandoraSparseMatching application.

Get matches using pandora in low resolution

Parameters

epipolar_image_left (CarsDataset) – tiled left epipolar CarsDataset contains:
epipolar_image_left –
tiled left epipolar CarsDataset contains:
- N x M Delayed tiles. Each tile will be a future xarray Dataset containing:
  - data with keys : “im”, “msk”, “color”
  - attrs with keys: “margins” with “disp_min” and “disp_max” “transform”, “crs”, “valid_pixels”, “no_data_mask”, “no_data_img”
- attributes containing:
  ”largest_epipolar_region”,”opt_epipolar_tile_size”
epipolar_image_right (CarsDataset) –
tiled right epipolar CarsDataset contains:
- N x M Delayed tiles. Each tile will be a future xarray Dataset containing:
  - data with keys : “im”, “msk”, “color”
  - attrs with keys: “margins” with “disp_min” and “disp_max”
    ”transform”, “crs”, “valid_pixels”, “no_data_mask”, “no_data_img”
- attributes containing:
  ”largest_epipolar_region”,”opt_epipolar_tile_size”
orchestrator – orchestrator used
pair_folder (str) – folder used for current pair
pair_key (str) – pair id
disp_to_alt_ratio (float) – disp to alti ratio used for performance map

Returns

left matches, right matches. Each CarsDataset contains:

N x M Delayed tiles Each tile will be a future pandas DataFrame containing:
- data : (L, 4) shape matches
attributes containing “disp_lower_bound”, “disp_upper_bound”, “elevation_delta_lower_bound”,”elevation_delta_upper_bound”

Return type

Tuple(CarsDataset, CarsDataset)

cars.applications.sparse_matching.pandora_sparse_matching.compute_pandora_matches_wrapper(left_image_object: xarray.Dataset, right_image_object: xarray.Dataset, corr_conf, disp_upper_bound, disp_lower_bound, resolution, saving_info_matches=None, saving_info_disparity_map=None) → Dict[str, Tuple[xarray.Dataset, xarray.Dataset]][source]

Compute pandora matches from image objects. This function will be run as a delayed task.

User must provide saving infos to save properly created datasets