cars.applications.point_cloud_outlier_removal.pc_out_removal

this module contains the abstract PointsCloudOutlierRemoval application class.

Module Contents

Classes

PointCloudOutlierRemoval

PointCloudOutlierRemoval
class cars.applications.point_cloud_outlier_removal.pc_out_removal.PointCloudOutlierRemoval(conf=None)[source]

Bases: cars.applications.application_template.ApplicationTemplate

PointCloudOutlierRemoval

available_applications: Dict
default_application = 'statistical'
classmethod __init_subclass__(short_name, **kwargs)[source]
abstract get_on_ground_margin(resolution=0.5)[source]

Get margins to use during point clouds fusion

Returns

margin

Return type

float

abstract get_method()[source]

Get margins to use during point clouds fusion

Returns

algorithm method

Return type

string

abstract get_optimal_tile_size(max_ram_per_worker, superposing_point_clouds=1, point_cloud_resolution=0.5)[source]

Get the optimal tile size to use, depending on memory available

Parameters

  • max_ram_per_worker (int) – maximum ram available

  • superposing_point_clouds (int) – number of point clouds superposing

  • point_cloud_resolution (float) – resolution of point cloud

Returns

optimal tile size in meter

Return type

float

__register_epipolar_dataset__(merged_point_cloud, depth_map_dir=None, dump_dir=None, app_name='', pair_key='PAIR_0')[source]

Create dataset and registered the output in the orchestrator. the output X, Y and Z ground coordinates will be saved in depth_map_dir if the parameter is no None. Alternatively it will be saved to dump_dir if save_intermediate_data is set and depth_map_dir is None.

Parameters

  • merged_point_cloud (CarsDataset) – Merged point cloud

  • depth_map_dir (str) – output depth map directory. If None output will be written in dump_dir if intermediate data is requested

  • dump_dir (str) – dump dir for output (except depth map) if intermediate data is requested

  • app_name (str) – application name for file names

  • pair_key (str) – name of current pair for index registration

Returns

Filtered point cloud

Return type

CarsDataset

__register_pc_dataset__(merged_point_cloud=None, point_cloud_dir=None, dump_dir=None, app_name=None)[source]

Create dataset and registered the output in the orchestrator. The point cloud dataset can be saved as laz using the save_laz_output option. Alternatively, the point cloud will be saved as laz and csv in the dump directory if the application save_intermediate data configuration parameter is set.

Parameters

  • merged_point_cloud (CarsDataset) – Merged point cloud

  • point_cloud_dir (str) – output depth map directory. If None output will be written in dump_dir if intermediate data is requested

  • dump_dir (str) – dump dir for output (except depth map) if intermediate data is requested

  • app_name (str) – application name for file names

Returns

Filtered point cloud

Return type

CarsDataset

abstract run(merged_point_cloud, orchestrator=None, save_laz_output=False, depth_map_dir=None, point_cloud_dir=None, dump_dir=None, epsg=None)[source]

Run PointCloudOutlierRemoval application.

Creates a CarsDataset filled with new point cloud tiles.

Parameters

  • merged_point_cloud (CarsDataset filled with pandas.DataFrame) – merged point cloud

  • orchestrator – orchestrator used

  • save_laz_output (bool) – save output point cloud as laz

  • output_dir (str) – output depth map directory. If None output will be written in dump_dir if intermediate data is requested

  • dump_dir (str) – dump dir for output (except depth map) if intermediate data is requested

  • epsg (int) – cartographic reference for the point cloud (array input)

Returns

filtered merged point cloud

Return type

CarsDataset filled with xr.Dataset