cars.applications.point_cloud_fusion.point_cloud_fusion

this module contains the abstract PointCloudFusion application class.

Module Contents

Classes

PointCloudFusion

PointCloudFusion

class cars.applications.point_cloud_fusion.point_cloud_fusion.PointCloudFusion(conf=None)

Bases: cars.applications.application_template.ApplicationTemplate

PointCloudFusion

available_applications: Dict

default_application = 'mapping_to_terrain_tiles'

classmethod __init_subclass__(short_name, **kwargs)

abstract run(list_epipolar_point_clouds, bounds, epsg, source_pc_names=None, orchestrator=None, margins=0, optimal_terrain_tile_width=500, roi=None)

Run EpipolarCloudFusion application.

Creates a CarsDataset corresponding to the merged point clouds, tiled with the terrain grid used during rasterization.

Parameters

• list_epipolar_point_clouds (list(CarsDataset) filled with xr.Dataset) –

  list with point clouds Each CarsDataset contains:

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

    • data : with keys : “x”, “y”, “z”, “corr_msk” optional: “color”, “msk”, “z_inf”, “z_sup”

    • attrs with keys: “margins”, “epi_full_size”, “epsg”

  • attributes containing: “disp_lower_bound”, “disp_upper_bound” “elevation_delta_lower_bound”, “elevation_delta_upper_bound”

• bounds (list) – terrain bounds

• epsg (str) – epsg to use

• source_pc_names (list[str]) – source pc names

• orchestrator (Orchestrator) – orchestrator used

• margins (float) – margins needed for tiles, meter or degree

• optimal_terrain_tile_width (int) – optimal terrain tile width

Returns

Merged point clouds

CarsDataset contains:

• Z x W Delayed tiles Each tile will be a future pandas DataFrame containing:

  • data : with keys : “x”, “y”, “z”, “corr_msk” optional: “clr”, “msk”, “data_valid”,”coord_epi_geom_i”, “coord_epi_geom_j”,”idx_im_epi”, “z_inf”, “z_sup”

  • attrs with keys: “epsg”

• attributes containing: “bounds”, “epsg”

Return type

CarsDataset filled with pandas.DataFrame