def calculate_features(im_ms, cloud_mask, im_bool):
"""
Calculates a range of features on the image that are used for the supervised classification.
The features include spectral normalized-difference indices and standard deviation of the image.
KV WRL 2018
Arguments:
-----------
im_ms: np.array
RGB + downsampled NIR and SWIR
cloud_mask: np.array
2D cloud mask with True where cloud pixels are
im_bool: np.array
2D array of boolean indicating where on the image to calculate the features
Returns: -----------
features: np.array
matrix containing each feature (columns) calculated for all
the pixels (rows) indicated in im_bool
"""
# add all the multispectral bands
features = np.expand_dims(im_ms[im_bool,0],axis=1)
for k in range(1,im_ms.shape[2]):
feature = np.expand_dims(im_ms[im_bool,k],axis=1)
features = np.append(features, feature, axis=-1)
# NIR-G
im_NIRG = SDS_tools.nd_index(im_ms[:,:,3], im_ms[:,:,1], cloud_mask)
features = np.append(features, np.expand_dims(im_NIRG[im_bool],axis=1), axis=-1)
# SWIR-G
im_SWIRG = SDS_tools.nd_index(im_ms[:,:,4], im_ms[:,:,1], cloud_mask)
features = np.append(features, np.expand_dims(im_SWIRG[im_bool],axis=1), axis=-1)
# NIR-R
im_NIRR = SDS_tools.nd_index(im_ms[:,:,3], im_ms[:,:,2], cloud_mask)
features = np.append(features, np.expand_dims(im_NIRR[im_bool],axis=1), axis=-1)
# SWIR-NIR
im_SWIRNIR = SDS_tools.nd_index(im_ms[:,:,4], im_ms[:,:,3], cloud_mask)
features = np.append(features, np.expand_dims(im_SWIRNIR[im_bool],axis=1), axis=-1)
# B-R
im_BR = SDS_tools.nd_index(im_ms[:,:,0], im_ms[:,:,2], cloud_mask)
features = np.append(features, np.expand_dims(im_BR[im_bool],axis=1), axis=-1)
# calculate standard deviation of individual bands
for k in range(im_ms.shape[2]):
im_std = SDS_tools.image_std(im_ms[:,:,k], 1)
features = np.append(features, np.expand_dims(im_std[im_bool],axis=1), axis=-1)
# calculate standard deviation of the spectral indices
im_std = SDS_tools.image_std(im_NIRG, 1)
features = np.append(features, np.expand_dims(im_std[im_bool],axis=1), axis=-1)
im_std = SDS_tools.image_std(im_SWIRG, 1)
features = np.append(features, np.expand_dims(im_std[im_bool],axis=1), axis=-1)
im_std = SDS_tools.image_std(im_NIRR, 1)
features = np.append(features, np.expand_dims(im_std[im_bool],axis=1), axis=-1)
im_std = SDS_tools.image_std(im_SWIRNIR, 1)
features = np.append(features, np.expand_dims(im_std[im_bool],axis=1), axis=-1)
im_std = SDS_tools.image_std(im_BR, 1)
features = np.append(features, np.expand_dims(im_std[im_bool],axis=1), axis=-1)
return features
def merge_overlapping_images(metadata,inputs):
"""
Merge simultaneous overlapping images that cover the area of interest.
When the area of interest is located at the boundary between 2 images, there
will be overlap between the 2 images and both will be downloaded from Google
Earth Engine. This function merges the 2 images, so that the area of interest
is covered by only 1 image.
KV WRL 2018
Arguments:
-----------
metadata: dict
contains all the information about the satellite images that were downloaded
inputs: dict with the following keys
'sitename': str
name of the site
'polygon': list
polygon containing the lon/lat coordinates to be extracted,
longitudes in the first column and latitudes in the second column,
there are 5 pairs of lat/lon with the fifth point equal to the first point:
```
polygon = [[[151.3, -33.7],[151.4, -33.7],[151.4, -33.8],[151.3, -33.8],
[151.3, -33.7]]]
```
'dates': list of str
list that contains 2 strings with the initial and final dates in
format 'yyyy-mm-dd':
```
dates = ['1987-01-01', '2018-01-01']
```
'sat_list': list of str
list that contains the names of the satellite missions to include:
```
sat_list = ['L5', 'L7', 'L8', 'S2']
```
'filepath_data': str
filepath to the directory where the images are downloaded
Returns:
-----------
metadata_updated: dict
updated metadata
"""
# only for Sentinel-2 at this stage (not sure if this is needed for Landsat images)
sat = 'S2'
filepath = os.path.join(inputs['filepath'], inputs['sitename'])
filenames = metadata[sat]['filenames']
# find the pairs of images that are within 5 minutes of each other
time_delta = 5*60 # 5 minutes in seconds
dates = metadata[sat]['dates'].copy()
pairs = []
for i,date in enumerate(metadata[sat]['dates']):
# dummy value so it does not match it again
dates[i] = pytz.utc.localize(datetime(1,1,1) + timedelta(days=i+1))
# calculate time difference
time_diff = np.array([np.abs((date - _).total_seconds()) for _ in dates])
# find the matching times and add to pairs list
boolvec = time_diff <= time_delta
if np.sum(boolvec) == 0:
continue
else:
idx_dup = np.where(boolvec)[0][0]
pairs.append([i,idx_dup])
# for each pair of image, create a mask and add no_data into the .tif file (this is needed before merging .tif files)
for i,pair in enumerate(pairs):
fn_im = []
for index in range(len(pair)):
# get filenames of all the files corresponding to the each image in the pair
fn_im.append([os.path.join(filepath, 'S2', '10m', filenames[pair[index]]),
os.path.join(filepath, 'S2', '20m', filenames[pair[index]].replace('10m','20m')),
os.path.join(filepath, 'S2', '60m', filenames[pair[index]].replace('10m','60m')),
os.path.join(filepath, 'S2', 'meta', filenames[pair[index]].replace('_10m','').replace('.tif','.txt'))])
# read that image
im_ms, georef, cloud_mask, im_extra, im_QA, im_nodata = SDS_preprocess.preprocess_single(fn_im[index], sat, False)
# im_RGB = SDS_preprocess.rescale_image_intensity(im_ms[:,:,[2,1,0]], cloud_mask, 99.9)
# in Sentinel2 images close to the edge of the image there are some artefacts,
# that are squares with constant pixel intensities. They need to be masked in the
# raster (GEOTIFF). It can be done using the image standard deviation, which
# indicates values close to 0 for the artefacts.
if len(im_ms) > 0:
# calculate image std for the first 10m band
im_std = SDS_tools.image_std(im_ms[:,:,0],1)
# convert to binary
im_binary = np.logical_or(im_std < 1e-6, np.isnan(im_std))
# dilate to fill the edges (which have high std)
mask10 = morphology.dilation(im_binary, morphology.square(3))
# mask all 10m bands
for k in range(im_ms.shape[2]):
im_ms[mask10,k] = np.nan
# mask the 10m .tif file (add no_data where mask is True)
SDS_tools.mask_raster(fn_im[index][0], mask10)
# create another mask for the 20m band (SWIR1)
im_std = SDS_tools.image_std(im_extra,1)
im_binary = np.logical_or(im_std < 1e-6, np.isnan(im_std))
mask20 = morphology.dilation(im_binary, morphology.square(3))
im_extra[mask20] = np.nan
# mask the 20m .tif file (im_extra)
SDS_tools.mask_raster(fn_im[index][1], mask20)
# use the 20m mask to create a mask for the 60m QA band (by resampling)
mask60 = ndimage.zoom(mask20,zoom=1/3,order=0)
mask60 = transform.resize(mask60, im_QA.shape, mode='constant', order=0,
preserve_range=True)
mask60 = mask60.astype(bool)
# mask the 60m .tif file (im_QA)
SDS_tools.mask_raster(fn_im[index][2], mask60)
else:
continue
# make a figure for quality control
# fig,ax= plt.subplots(2,2,tight_layout=True)
# ax[0,0].imshow(im_RGB)
# ax[0,0].set_title('RGB original')
# ax[1,0].imshow(mask10)
# ax[1,0].set_title('Mask 10m')
# ax[0,1].imshow(mask20)
# ax[0,1].set_title('Mask 20m')
# ax[1,1].imshow(mask60)
# ax[1,1].set_title('Mask 60 m')
# once all the pairs of .tif files have been masked with no_data, merge the using gdal_merge
fn_merged = os.path.join(filepath, 'merged.tif')
# merge masked 10m bands and remove duplicate file
gdal_merge.main(['', '-o', fn_merged, '-n', '0', fn_im[0][0], fn_im[1][0]])
os.chmod(fn_im[0][0], 0o777)
os.remove(fn_im[0][0])
os.chmod(fn_im[1][0], 0o777)
os.remove(fn_im[1][0])
os.chmod(fn_merged, 0o777)
os.rename(fn_merged, fn_im[0][0])
# merge masked 20m band (SWIR band)
gdal_merge.main(['', '-o', fn_merged, '-n', '0', fn_im[0][1], fn_im[1][1]])
os.chmod(fn_im[0][1], 0o777)
os.remove(fn_im[0][1])
os.chmod(fn_im[1][1], 0o777)
os.remove(fn_im[1][1])
os.chmod(fn_merged, 0o777)
os.rename(fn_merged, fn_im[0][1])
# merge QA band (60m band)
gdal_merge.main(['', '-o', fn_merged, '-n', '0', fn_im[0][2], fn_im[1][2]])
os.chmod(fn_im[0][2], 0o777)
os.remove(fn_im[0][2])
os.chmod(fn_im[1][2], 0o777)
os.remove(fn_im[1][2])
os.chmod(fn_merged, 0o777)
os.rename(fn_merged, fn_im[0][2])
# remove the metadata .txt file of the duplicate image
os.chmod(fn_im[1][3], 0o777)
os.remove(fn_im[1][3])
print('%d pairs of overlapping Sentinel-2 images were merged' % len(pairs))
# update the metadata dict
metadata_updated = copy.deepcopy(metadata)
idx_removed = []
idx_kept = []
for pair in pairs: idx_removed.append(pair[1])
for idx in np.arange(0,len(metadata[sat]['dates'])):
if not idx in idx_removed: idx_kept.append(idx)
for key in metadata_updated[sat].keys():
metadata_updated[sat][key] = [metadata_updated[sat][key][_] for _ in idx_kept]
return metadata_updated
def merge_overlapping_images(metadata, inputs):
"""
Merge simultaneous overlapping images that cover the area of interest.
When the area of interest is located at the boundary between 2 images, there
will be overlap between the 2 images and both will be downloaded from Google
Earth Engine. This function merges the 2 images, so that the area of interest
is covered by only 1 image.
KV WRL 2018
Arguments:
-----------
metadata: dict
contains all the information about the satellite images that were downloaded
inputs: dict with the following keys
'sitename': str
name of the site
'polygon': list
polygon containing the lon/lat coordinates to be extracted,
longitudes in the first column and latitudes in the second column,
there are 5 pairs of lat/lon with the fifth point equal to the first point:
```
polygon = [[[151.3, -33.7],[151.4, -33.7],[151.4, -33.8],[151.3, -33.8],
[151.3, -33.7]]]
```
'dates': list of str
list that contains 2 strings with the initial and final dates in
format 'yyyy-mm-dd':
```
dates = ['1987-01-01', '2018-01-01']
```
'sat_list': list of str
list that contains the names of the satellite missions to include:
```
sat_list = ['L5', 'L7', 'L8', 'S2']
```
'filepath_data': str
filepath to the directory where the images are downloaded
Returns:
-----------
metadata_updated: dict
updated metadata
"""
# only for Sentinel-2 at this stage (not sure if this is needed for Landsat images)
sat = 'S2'
filepath = os.path.join(inputs['filepath'], inputs['sitename'])
filenames = metadata[sat]['filenames']
# find the pairs of images that are within 5 minutes of each other
time_delta = 5 * 60 # 5 minutes in seconds
dates = metadata[sat]['dates'].copy()
pairs = []
for i, date in enumerate(metadata[sat]['dates']):
# dummy value so it does not match it again
dates[i] = pytz.utc.localize(datetime(1, 1, 1) + timedelta(days=i + 1))
# calculate time difference
time_diff = np.array(
[np.abs((date - _).total_seconds()) for _ in dates])
# find the matching times and add to pairs list
boolvec = time_diff <= time_delta
if np.sum(boolvec) == 0:
continue
else:
idx_dup = np.where(boolvec)[0][0]
pairs.append([i, idx_dup])
# because they could be triplicates in S2 images, adjust the pairs for consecutive merges
for i in range(1, len(pairs)):
if pairs[i - 1][1] == pairs[i][0]:
pairs[i][0] = pairs[i - 1][0]
# check also for quadruplicates and remove them
pair_first = [_[0] for _ in pairs]
for idx in np.unique(pair_first):
# quadruplicate if trying to merge 3 times the same image with a successive
if sum(pair_first == idx) == 3:
# remove the last image: 3 .tif files + the .txt file
idx_last = [pairs[_]
for _ in np.where(pair_first == idx)[0]][-1][1]
fn_im = [
os.path.join(filepath, 'S2', '10m', filenames[idx_last]),
os.path.join(filepath, 'S2', '20m',
filenames[idx_last].replace('10m', '20m')),
os.path.join(filepath, 'S2', '60m',
filenames[idx_last].replace('10m', '60m')),
os.path.join(
filepath, 'S2', 'meta',
filenames[idx_last].replace('_10m',
'').replace('.tif', '.txt'))
]
for k in range(4):
os.chmod(fn_im[k], 0o777)
os.remove(fn_im[k])
# remove that pair from the list
pairs.pop(np.where(pair_first == idx)[0][-1])
# for each pair of image, first check if one image completely contains the other
# in that case keep the larger image. Otherwise merge the two images.
for i, pair in enumerate(pairs):
# get filenames of all the files corresponding to the each image in the pair
fn_im = []
for index in range(len(pair)):
fn_im.append([
os.path.join(filepath, 'S2', '10m', filenames[pair[index]]),
os.path.join(filepath, 'S2', '20m',
filenames[pair[index]].replace('10m', '20m')),
os.path.join(filepath, 'S2', '60m',
filenames[pair[index]].replace('10m', '60m')),
os.path.join(
filepath, 'S2', 'meta',
filenames[pair[index]].replace('_10m',
'').replace('.tif', '.txt'))
])
# get polygon for first image
polygon0 = SDS_tools.get_image_bounds(fn_im[0][0])
im_epsg0 = metadata[sat]['epsg'][pair[0]]
# get polygon for second image
polygon1 = SDS_tools.get_image_bounds(fn_im[1][0])
im_epsg1 = metadata[sat]['epsg'][pair[1]]
# check if epsg are the same
if not im_epsg0 == im_epsg1:
print(
'WARNING: there was an error as two S2 images do not have the same epsg,'
+
' please open an issue on Github at https://github.com/kvos/CoastSat/issues'
+ ' and include your script so we can find out what happened.')
break
# check if one image contains the other one
if polygon0.contains(polygon1):
# if polygon0 contains polygon1, remove files for polygon1
for k in range(4): # remove the 3 .tif files + the .txt file
os.chmod(fn_im[1][k], 0o777)
os.remove(fn_im[1][k])
# print('removed 1')
continue
elif polygon1.contains(polygon0):
# if polygon1 contains polygon0, remove image0
for k in range(4): # remove the 3 .tif files + the .txt file
os.chmod(fn_im[0][k], 0o777)
os.remove(fn_im[0][k])
# print('removed 0')
# adjust the order in case of triplicates
if i + 1 < len(pairs):
if pairs[i + 1][0] == pair[0]: pairs[i + 1][0] = pairs[i][1]
continue
# otherwise merge the two images after masking the nodata values
else:
for index in range(len(pair)):
# read image
im_ms, georef, cloud_mask, im_extra, im_QA, im_nodata = SDS_preprocess.preprocess_single(
fn_im[index], sat, False)
# in Sentinel2 images close to the edge of the image there are some artefacts,
# that are squares with constant pixel intensities. They need to be masked in the
# raster (GEOTIFF). It can be done using the image standard deviation, which
# indicates values close to 0 for the artefacts.
if len(im_ms) > 0:
# calculate image std for the first 10m band
im_std = SDS_tools.image_std(im_ms[:, :, 0], 1)
# convert to binary
im_binary = np.logical_or(im_std < 1e-6, np.isnan(im_std))
# dilate to fill the edges (which have high std)
mask10 = morphology.dilation(im_binary,
morphology.square(3))
# mask the 10m .tif file (add no_data where mask is True)
SDS_tools.mask_raster(fn_im[index][0], mask10)
# now calculate the mask for the 20m band (SWIR1)
# for the older version of the ee api calculate the image std again
if int(ee.__version__[-3:]) <= 201:
# calculate std to create another mask for the 20m band (SWIR1)
im_std = SDS_tools.image_std(im_extra, 1)
im_binary = np.logical_or(im_std < 1e-6,
np.isnan(im_std))
mask20 = morphology.dilation(im_binary,
morphology.square(3))
# for the newer versions just resample the mask for the 10m bands
else:
# create mask for the 20m band (SWIR1) by resampling the 10m one
mask20 = ndimage.zoom(mask10, zoom=1 / 2, order=0)
mask20 = transform.resize(mask20,
im_extra.shape,
mode='constant',
order=0,
preserve_range=True)
mask20 = mask20.astype(bool)
# mask the 20m .tif file (im_extra)
SDS_tools.mask_raster(fn_im[index][1], mask20)
# create a mask for the 60m QA band by resampling the 20m one
mask60 = ndimage.zoom(mask20, zoom=1 / 3, order=0)
mask60 = transform.resize(mask60,
im_QA.shape,
mode='constant',
order=0,
preserve_range=True)
mask60 = mask60.astype(bool)
# mask the 60m .tif file (im_QA)
SDS_tools.mask_raster(fn_im[index][2], mask60)
# make a figure for quality control/debugging
# im_RGB = SDS_preprocess.rescale_image_intensity(im_ms[:,:,[2,1,0]], cloud_mask, 99.9)
# fig,ax= plt.subplots(2,3,tight_layout=True)
# ax[0,0].imshow(im_RGB)
# ax[0,0].set_title('RGB original')
# ax[1,0].imshow(mask10)
# ax[1,0].set_title('Mask 10m')
# ax[0,1].imshow(mask20)
# ax[0,1].set_title('Mask 20m')
# ax[1,1].imshow(mask60)
# ax[1,1].set_title('Mask 60 m')
# ax[0,2].imshow(im_QA)
# ax[0,2].set_title('Im QA')
# ax[1,2].imshow(im_nodata)
# ax[1,2].set_title('Im nodata')
else:
continue
# once all the pairs of .tif files have been masked with no_data, merge the using gdal_merge
fn_merged = os.path.join(filepath, 'merged.tif')
for k in range(3):
# merge masked bands
gdal_merge.main(
['', '-o', fn_merged, '-n', '0', fn_im[0][k], fn_im[1][k]])
# remove old files
os.chmod(fn_im[0][k], 0o777)
os.remove(fn_im[0][k])
os.chmod(fn_im[1][k], 0o777)
os.remove(fn_im[1][k])
# rename new file
fn_new = fn_im[0][k].split('.')[0] + '_merged.tif'
os.chmod(fn_merged, 0o777)
os.rename(fn_merged, fn_new)
# open both metadata files
metadict0 = dict([])
with open(fn_im[0][3], 'r') as f:
metadict0['filename'] = f.readline().split('\t')[1].replace(
'\n', '')
metadict0['acc_georef'] = float(
f.readline().split('\t')[1].replace('\n', ''))
metadict0['epsg'] = int(f.readline().split('\t')[1].replace(
'\n', ''))
metadict1 = dict([])
with open(fn_im[1][3], 'r') as f:
metadict1['filename'] = f.readline().split('\t')[1].replace(
'\n', '')
metadict1['acc_georef'] = float(
f.readline().split('\t')[1].replace('\n', ''))
metadict1['epsg'] = int(f.readline().split('\t')[1].replace(
'\n', ''))
# check if both images have the same georef accuracy
if np.any(
np.array([
metadict0['acc_georef'], metadict1['acc_georef']
]) == -1):
metadict0['georef'] = -1
# add new name
metadict0['filename'] = metadict0['filename'].split(
'.')[0] + '_merged.tif'
# remove the old metadata.txt files
os.chmod(fn_im[0][3], 0o777)
os.remove(fn_im[0][3])
os.chmod(fn_im[1][3], 0o777)
os.remove(fn_im[1][3])
# rewrite the .txt file with a new metadata file
fn_new = fn_im[0][3].split('.')[0] + '_merged.txt'
with open(fn_new, 'w') as f:
for key in metadict0.keys():
f.write('%s\t%s\n' % (key, metadict0[key]))
# update filenames list (in case there are triplicates)
filenames[pair[0]] = metadict0['filename']
print(
'%d out of %d Sentinel-2 images were merged (overlapping or duplicate)'
% (len(pairs), len(filenames)))
# update the metadata dict
metadata_updated = get_metadata(inputs)
return metadata_updated
def merge_overlapping_images(metadata,inputs):
"""
When the area of interest is located at the boundary between 2 images, there will be overlap
between the 2 images and both will be downloaded from Google Earth Engine. This function
merges the 2 images, so that the area of interest is covered by only 1 image.
KV WRL 2018
Arguments:
-----------
metadata: dict
contains all the information about the satellite images that were downloaded
inputs: dict
dictionnary that contains the following fields:
'sitename': str
String containig the name of the site
'polygon': list
polygon containing the lon/lat coordinates to be extracted,
longitudes in the first column and latitudes in the second column,
there are 5 pairs of lat/lon with the fifth point equal to the first point.
e.g. [[[151.3, -33.7],[151.4, -33.7],[151.4, -33.8],[151.3, -33.8],
[151.3, -33.7]]]
'dates': list of str
list that contains 2 strings with the initial and final dates in format 'yyyy-mm-dd'
e.g. ['1987-01-01', '2018-01-01']
'sat_list': list of str
list that contains the names of the satellite missions to include
e.g. ['L5', 'L7', 'L8', 'S2']
'filepath_data': str
Filepath to the directory where the images are downloaded
Returns:
-----------
metadata_updated: dict
updated metadata with the information of the merged images
"""
# only for Sentinel-2 at this stage (not sure if this is needed for Landsat images)
sat = 'S2'
filepath = os.path.join(inputs['filepath'], inputs['sitename'])
# find the images that are overlapping (same date in S2 filenames)
filenames = metadata[sat]['filenames']
filenames_copy = filenames.copy()
# loop through all the filenames and find the pairs of overlapping images (same date and time of acquisition)
pairs = []
for i,fn in enumerate(filenames):
filenames_copy[i] = []
# find duplicate
boolvec = [fn[:22] == _[:22] for _ in filenames_copy]
if np.any(boolvec):
idx_dup = np.where(boolvec)[0][0]
if len(filenames[i]) > len(filenames[idx_dup]):
pairs.append([idx_dup,i])
else:
pairs.append([i,idx_dup])
# for each pair of images, merge them into one complete image
for i,pair in enumerate(pairs):
fn_im = []
for index in range(len(pair)):
# read image
fn_im.append([os.path.join(filepath, 'S2', '10m', filenames[pair[index]]),
os.path.join(filepath, 'S2', '20m', filenames[pair[index]].replace('10m','20m')),
os.path.join(filepath, 'S2', '60m', filenames[pair[index]].replace('10m','60m')),
os.path.join(filepath, 'S2', 'meta', filenames[pair[index]].replace('_10m','').replace('.tif','.txt'))])
im_ms, georef, cloud_mask, im_extra, im_QA, im_nodata = SDS_preprocess.preprocess_single(fn_im[index], sat, False)
# in Sentinel2 images close to the edge of the image there are some artefacts,
# that are squares with constant pixel intensities. They need to be masked in the
# raster (GEOTIFF). It can be done using the image standard deviation, which
# indicates values close to 0 for the artefacts.
# First mask the 10m bands
if len(im_ms) > 0:
im_std = SDS_tools.image_std(im_ms[:,:,0],1)
im_binary = np.logical_or(im_std < 1e-6, np.isnan(im_std))
mask = morphology.dilation(im_binary, morphology.square(3))
for k in range(im_ms.shape[2]):
im_ms[mask,k] = np.nan
SDS_tools.mask_raster(fn_im[index][0], mask)
# Then mask the 20m band
im_std = SDS_tools.image_std(im_extra,1)
im_binary = np.logical_or(im_std < 1e-6, np.isnan(im_std))
mask = morphology.dilation(im_binary, morphology.square(3))
im_extra[mask] = np.nan
SDS_tools.mask_raster(fn_im[index][1], mask)
else:
continue
# make a figure for quality control
# plt.figure()
# plt.subplot(221)
# plt.imshow(im_ms[:,:,[2,1,0]])
# plt.title('imRGB')
# plt.subplot(222)
# plt.imshow(im20, cmap='gray')
# plt.title('im20')
# plt.subplot(223)
# plt.imshow(imQA, cmap='gray')
# plt.title('imQA')
# plt.subplot(224)
# plt.title(fn_im[index][0][-30:])
# merge masked 10m bands
fn_merged = os.path.join(os.getcwd(), 'merged.tif')
gdal_merge.main(['', '-o', fn_merged, '-n', '0', fn_im[0][0], fn_im[1][0]])
os.chmod(fn_im[0][0], 0o777)
os.remove(fn_im[0][0])
os.chmod(fn_im[1][0], 0o777)
os.remove(fn_im[1][0])
os.rename(fn_merged, fn_im[0][0])
# merge masked 20m band (SWIR band)
fn_merged = os.path.join(os.getcwd(), 'merged.tif')
gdal_merge.main(['', '-o', fn_merged, '-n', '0', fn_im[0][1], fn_im[1][1]])
os.chmod(fn_im[0][1], 0o777)
os.remove(fn_im[0][1])
os.chmod(fn_im[1][1], 0o777)
os.remove(fn_im[1][1])
os.rename(fn_merged, fn_im[0][1])
# merge QA band (60m band)
fn_merged = os.path.join(os.getcwd(), 'merged.tif')
gdal_merge.main(['', '-o', fn_merged, '-n', 'nan', fn_im[0][2], fn_im[1][2]])
os.chmod(fn_im[0][2], 0o777)
os.remove(fn_im[0][2])
os.chmod(fn_im[1][2], 0o777)
os.remove(fn_im[1][2])
os.rename(fn_merged, fn_im[0][2])
# remove the metadata .txt file of the duplicate image
os.chmod(fn_im[1][3], 0o777)
os.remove(fn_im[1][3])
print('%d pairs of overlapping Sentinel-2 images were merged' % len(pairs))
# update the metadata dict (delete all the duplicates)
metadata_updated = copy.deepcopy(metadata)
filenames_copy = metadata_updated[sat]['filenames']
index_list = []
for i in range(len(filenames_copy)):
if filenames_copy[i].find('dup') == -1:
index_list.append(i)
for key in metadata_updated[sat].keys():
metadata_updated[sat][key] = [metadata_updated[sat][key][_] for _ in index_list]
return metadata_updated