cars.applications.point_cloud_fusion.mapping_to_terrain_tiles

this module contains the epipolar cloud fusion application class.

Module Contents

Classes

MappingToTerrainTiles

EpipolarCloudFusion

Functions

compute_point_cloud_wrapper(point_clouds_left, ...)

Wrapper for points clouds fusion step :

simple_merged_point_cloud_dataset(→ pandas.DataFrame)

Wrapper of simple_rasterization
class cars.applications.point_cloud_fusion.mapping_to_terrain_tiles.MappingToTerrainTiles(conf=None)

Bases: cars.applications.point_cloud_fusion.point_cloud_fusion.PointCloudFusion

EpipolarCloudFusion

check_conf(conf)

Check configuration

Parameters

conf (dict) – configuration to check

Returns

overloaded configuration

Return type

dict

pre_run(bounds, optimal_terrain_tile_width)

Pre run some computations

Returns

bounds, terrain_grid

run(list_epipolar_points_cloud_left, list_epipolar_points_cloud_right, bounds, epsg, orchestrator=None, margins=None, on_ground_margin=0, optimal_terrain_tile_width=500)

Run EpipolarCloudFusion application.

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

Parameters

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

    list with left points 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”,

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

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

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

    list with right points 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”,

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

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

  • bounds (list) – terrain bounds

  • epsg (str) – epsg to use

  • orchestrator (Orchestrator) – orchestrator used

  • margins (dict ex: {"radius": 1, "resolution": 0.5}) – margins to add to tiles

  • on_ground_margin (float) – margins needed for future filtering

  • optimal_terrain_tile_width (int) – optimal terrain tile width

Returns

Merged points 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”

    • attrs with keys: “epsg”

  • attributes contraining: “bounds”, “ysize”, “xsize”, “epsg”

Return type

CarsDataset filled with pandas.DataFrame

cars.applications.point_cloud_fusion.mapping_to_terrain_tiles.compute_point_cloud_wrapper(point_clouds_left, point_clouds_right, resolution, epsg, **kwargs)

Wrapper for points clouds fusion step : - Convert a list of clouds to correct epsg

Parameters

  • point_clouds_left (list(xr.Dataset)) –

    list of clouds, list of datasets with :

    • cst.X

    • cst.Y

    • cst.Z

    • cst.EPI_COLOR

  • point_clouds_right (list of DataObject) –

    list of cloud, list of datasets (list of None if use_sec_disp not activated) with :

    • cst.X

    • cst.Y

    • cst.Z

    • cst.EPI_COLOR

  • resolution (float) – Produced DSM resolution (meter, degree [EPSG dependent])

  • epsg_code (int) – epsg code for the CRS of the output DSM

  • stereo_out_epsg (int) – epsg code to convert point cloud to, if needed

Returns

merged points cloud dataframe with: - cst.X - cst.Y - cst.Z - cst.EPI_COLOR - attrs : xstart, ystart, xsize, ysize, saving_info

Return type

pandas.DataFrame

cars.applications.point_cloud_fusion.mapping_to_terrain_tiles.simple_merged_point_cloud_dataset(cloud_list: List[xarray.Dataset], resolution: float, epsg: int, xstart: float = None, ystart: float = None, xsize: int = None, ysize: int = None, radius: int = 1, on_ground_margin=0) → pandas.DataFrame

Wrapper of simple_rasterization that has xarray.Dataset as inputs and outputs.

Parameters

  • cloud_list – list of cloud points to rasterize

  • resolution – Resolution of rasterized cells, expressed in cloud CRS units or None

  • epsg – epsg code for the CRS of the final raster

  • xstart – xstart of the rasterization grid (if None, will be estimated by the function)

  • ystart – ystart of the rasterization grid (if None, will be estimated by the function)

  • xsize – xsize of the rasterization grid (if None, will be estimated by the function)

  • ysize – ysize of the rasterization grid (if None, will be estimated by the function)

  • radius (int) – rasterization radius

  • on_ground_margin (int) – point cloud filtering margin

Returns

cloud and Color