L1
Table of contents
- class l1.l1_event.L1C_event(tiles_collection=None, bands_names=None, event_class=None, event_name=None, device=device(type='cpu'))[source]
Creates an L1C image from a tiles collection and band_names. It is possible to associate an image class to the image.
- Parameters:
tiles_collection (list, optional) – list of L1C_tile. Defaults to None.
bands_names (list, optional) – list of band names. Defaults to None.
event_class (string, optional) – class name. Defaults to None.
event_name (str, optional) – event name. Defaults to None.
device (torch.device, optional) – device for each L0 tile in the image. Defaults to torch.device(“cpu”).
- crop_tile(l0_granule_coordinates, out_dir_path=None, out_name_ending=None, lat_lon_format=True, verbose=True, cfg_file_dict=None, id_l0_l1_dict=None, database='THRAWS', overwrite=False)[source]
Create a mosaic of l1 tiles and crop the mosaic by using the l0_granule_coordinates. The output file is saved as TIF file into the directory specified through “”out_dir_path””.
- Parameters:
l0_granule_coordinates (list) – list of coordinates of a referene l0_granule.
out_dir_path (src, optional) – path to the output directory containing the cropped TIF file. If None, default path is used. Defaults to None.
out_name_ending (src, optional) – optional ending for the output name. Defaults to None.
lat_lon_format (bool, optional) – if True, coordinates points are in (LAT, LON) format. Defaults to True.
verbose (bool, optional) – if True, verbose mode is used. Defaults to True.
cfg_file_dict (dict, optional) – dictionary containing paths to the different end2end directories. If None, internal CSV database will be parsed.
id_l0_l1_dict (dict, optional) – id-l0-l1 dictionary. If None, internal CSV database will be parsed.
database (string, optional) – database name. Defaults to “THRAWS”.
overwrite (bool, optional) – if True, the file is overwritten if exists, otherwise tile generation is skipped. Defaults to False.
- Returns:
output file name
- Return type:
src
- from_database(id_event, bands_list=None, cfg_file_dict=None, id_l0_l1_dict=None, reproject_bounds=True, verbose=True, database='THRAWS')[source]
Read specific bands of the L1 Sentine2 image “”id_event””, specified in “bands_list”, from database.
- Parameters:
id_event (str) – event ID.
bands_list (list, optional) – bands list. If None, all bands are used and sorted according to the datasheet order. Defaults to None.
cfg_file_dict (dict, optional) – dictionary containing paths to the different end2end directories. If None, internal CSV database will be parsed.
id_l0_l1_dict (dict, optional) – id-l0-l1 dictionary. If None, internal CSV database will be parsed.
reproject_bounds (bool, optional) – if True, bounds are reprojected to EPGS:4326.
verbose (bool, optional) – if True, if True, verbose mode is used. Defaults to True.
database (string, optional) – database name. Defaults to “THRAWS”.
- from_path(l1c_dir_path, bands_list, reproject_bounds=True, verbose=True)[source]
Read specific bands of the Sentinel-2 L0 event located at “”l0_dir_path””.
- Parameters:
l1c_dir_path (str) – path to the l0 event dir.
None (bands list. If) –
None. (all bands are used and sorted according to the datasheet order. Defaults to) –
reproject_bounds (bool, optional) – if True, bounds are reprojected to EPGS:4326.
verbose (bool, optional) – if True, if True, verbose mode is used. Defaults to True.
- get_bands_list()[source]
Returns the list of bands of every L1C_tile object in the collection.
- Returns:
band names.
- Return type:
list
- get_event_class()[source]
Get event class.
- Returns:
Returns {useful granules : bounding box dictionary}
- Return type:
dict
- get_tile(tile_idx)[source]
It returns the tile addressed by tile_idx.
- Parameters:
tile_idx (int) – tile index.
- get_tiles_info(tiles_idx=None)[source]
Return info of the tiles requested through tiles_idx from tiles names.
- Parameters:
tiles_idx (list, optional) – list of tiles for which getting the names.
None (If) –
None. (all the names of the tiles in the collection are returned. Defaults to) –
- Raises:
ValueError – Empty tiles lists
- Returns:
tiles name : tiles info
- Return type:
dictionary
- get_tiles_names(tiles_idx=None)[source]
Return names of the tiles requested through tiles_idx from tiles names.
- Parameters:
tiles_idx (list, optional) – list of tiles for which getting the names. If None, all the names of the tiles in the collection are returned. Defaults to None.
- Raises:
ValueError – Empty tiles lists
- Returns:
tiles’ names.
- Return type:
list
- is_void()[source]
Returns true if the image is void.
- Returns:
True if the image is void.
- Return type:
bool
- class l1.l1_tile.L1C_tile(tile_bands=None, bands_names=None, tile_name=None, tile_coordinates=None, tile_footprint_coordinates=None, bands_file_name_dict=None, crs=None, device=device(type='cpu'))[source]
Initialize an L0 tile.
- Parameters:
tile_bands (list, optional) – list of torch tensors representing each band in the format [H,W]. Defaults to None.
bands_names (list, optional) – list of band names. Defaults to None.
tile_name (string, optionl) – tile name. Defaults to None.
tile_coordinates (list, optional) – list containing [lan, lon] for every corner point. Defaults to None.
tile_footprint_coordinates (list, optional) – list containing [lan, lon] for every point of the tile. Defaults to None.
bands_file_name_dict (dict, optional) – dictionary associating the orginal jp2 file to each band. Defaults to None.
csr (string, optional) – crs. Defaults to None.
device (torch.device, optional) – torch.device. Defaults to torch.device(“cpu”).
- as_tensor(requested_bands=None, downsampling=True)[source]
Returns a tensor containing all the bands if all the requested bands have the same resolution.
- Parameters:
requested_bands (list, optional) – list of requested bands. If None, all the bands are used. Defaults to None.
downsampling (boolean, optional) – if True, bands are downsampled to the lowest resolution. Otherwise, they are upsampled to the highest one. Defaults to True.
- Raises:
ValueError – The tile is empty
- Returns:
tensor containing the requested bands.
- Return type:
torch.tensor
- create_tile(bands_list, tile_bands, tile_name, tile_coordinates, footprint_coordinates, bands_file_name_dict, crs)[source]
Creates a tile from the list of bands and from a torch tensor.
- Parameters:
bands_list (list) – list of band names.
tile_bands (list) – list of torch.tensors (bands) in format [H,W]
tile_name (str) – tile name.
tile_coordinates (list) – list of tile’s corners coordinates.
footprint_coordinates (list) – list of tile’s footprint’s coordinates.
bands_file_name_dict (dict) – bands_file_name_dict.
crs (string) – crs
- export_to_tif(save_path)[source]
Export to TIF file.
- Parameters:
save_path (str) – save path.
downsampling (bool, optional) – If True, bands are downsampled. Defaults to True.
- get_band(band_name)[source]
Returns a specific band as a tensor.
- Parameters:
band_name (string) – band name
- Returns:
requested band.
- Return type:
torch.tensor
- get_bands_file_name_dict()[source]
Returns the tile’s band_name jp2 dictionary.
- Returns:
tiles bands_file_name_dict.
- Return type:
dict
- get_tile_coordinates(latlon_format=True)[source]
Returns the tile’s coordinates. :param latlon_format: if True, LAT, LON format is used. Defaults to True. :type latlon_format: bool, optional
- Returns:
polygon coordinates.
- Return type:
list
- get_tile_footprint_coordinates()[source]
Returns the tile’s footprint coordinates.
- Returns:
polygon coordinates.
- Return type:
list
- get_tile_info()[source]
Returns name, sensing time, acquisition time, and coners coordinates.
- Returns:
name datetime: sensing time. datetime: acquisition time. list: tile’s corners’ coordinates. list: tile’s footprint’s coordinates.
- Return type:
string
- show_bands(requested_bands=None, downsampling=False, oversampling=False)[source]
It shows the requested bands.
- Parameters:
requested_bands (list, optional) – list of requested bands to show. If None, all the bands are shown. Defaults to None.
downsampling (bool, optional) – if True, bands are downsampled to have the same resolution. Default to False.
oversampling (bool, optional) – if True, bands are oversampled to have the same resolution. Downsampling has priority over upampling. Default to False.
- show_bands_superimposition(requested_bands=None, downsampling=True)[source]
It shows the superimposition of bands in requested_bands
- Parameters:
requested_bands (list, optional) – requested bands list. If None, all the bands are used. Defaults to None.
downsampling (boolean, optional) – if True, bands are downsampled to have the same resolution. Default to False.
- Raises:
ValueError – Impossible to superimpose more than 3 bands