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 extract_shorelines(metadata, settings):
"""
Extracts shorelines from satellite images.
KV WRL 2018
Arguments:
-----------
metadata: dict
contains all the information about the satellite images that were downloaded
settings: dict
contains the following fields:
sitename: str
String containig the name of the site
cloud_mask_issue: boolean
True if there is an issue with the cloud mask and sand pixels are being masked on the images
buffer_size: int
size of the buffer (m) around the sandy beach over which the pixels are considered in the
thresholding algorithm
min_beach_area: int
minimum allowable object area (in metres^2) for the class 'sand'
cloud_thresh: float
value between 0 and 1 defining the maximum percentage of cloud cover allowed in the images
output_epsg: int
output spatial reference system as EPSG code
check_detection: boolean
True to show each invidual detection and let the user validate the mapped shoreline
Returns:
-----------
output: dict
contains the extracted shorelines and corresponding dates.
"""
sitename = settings['inputs']['sitename']
filepath_data = settings['inputs']['filepath']
# initialise output structure
output = dict([])
# create a subfolder to store the .jpg images showing the detection
filepath_jpg = os.path.join(filepath_data, sitename, 'jpg_files',
'detection')
if not os.path.exists(filepath_jpg):
os.makedirs(filepath_jpg)
# close all open figures
plt.close('all')
print('Mapping shorelines:')
# loop through satellite list
for satname in metadata.keys():
# get images
filepath = SDS_tools.get_filepath(settings['inputs'], satname)
filenames = metadata[satname]['filenames']
# initialise the output variables
output_timestamp = [
] # datetime at which the image was acquired (UTC time)
output_shoreline = [] # vector of shoreline points
output_filename = [
] # filename of the images from which the shorelines where derived
output_cloudcover = [] # cloud cover of the images
output_geoaccuracy = [] # georeferencing accuracy of the images
output_idxkeep = [
] # index that were kept during the analysis (cloudy images are skipped)
# load classifiers and
if satname in ['L5', 'L7', 'L8']:
pixel_size = 15
if settings['dark_sand']:
clf = joblib.load(
os.path.join(os.getcwd(), 'classifiers',
'NN_4classes_Landsat_dark.pkl'))
else:
clf = joblib.load(
os.path.join(os.getcwd(), 'classifiers',
'NN_4classes_Landsat.pkl'))
elif satname == 'S2':
pixel_size = 10
clf = joblib.load(
os.path.join(os.getcwd(), 'classifiers', 'NN_4classes_S2.pkl'))
# convert settings['min_beach_area'] and settings['buffer_size'] from metres to pixels
buffer_size_pixels = np.ceil(settings['buffer_size'] / pixel_size)
min_beach_area_pixels = np.ceil(settings['min_beach_area'] /
pixel_size**2)
# loop through the images
for i in range(len(filenames)):
print('\r%s: %d%%' %
(satname, int(((i + 1) / len(filenames)) * 100)),
end='')
# get image filename
fn = SDS_tools.get_filenames(filenames[i], filepath, satname)
# preprocess image (cloud mask + pansharpening/downsampling)
im_ms, georef, cloud_mask, im_extra, imQA = SDS_preprocess.preprocess_single(
fn, satname, settings['cloud_mask_issue'])
# get image spatial reference system (epsg code) from metadata dict
image_epsg = metadata[satname]['epsg'][i]
# calculate cloud cover
cloud_cover = np.divide(
sum(sum(cloud_mask.astype(int))),
(cloud_mask.shape[0] * cloud_mask.shape[1]))
# skip image if cloud cover is above threshold
if cloud_cover > settings['cloud_thresh']:
continue
# classify image in 4 classes (sand, whitewater, water, other) with NN classifier
im_classif, im_labels = classify_image_NN(im_ms, im_extra,
cloud_mask,
min_beach_area_pixels,
clf)
# calculate a buffer around the reference shoreline (if any has been digitised)
im_ref_buffer = create_shoreline_buffer(cloud_mask.shape, georef,
image_epsg, pixel_size,
settings)
# there are two options to extract to map the contours:
# if there are pixels in the 'sand' class --> use find_wl_contours2 (enhanced)
# otherwise use find_wl_contours2 (traditional)
try: # use try/except structure for long runs
if sum(sum(im_labels[:, :, 0])) == 0:
# compute MNDWI image (SWIR-G)
im_mndwi = SDS_tools.nd_index(im_ms[:, :, 4],
im_ms[:, :, 1], cloud_mask)
# find water contours on MNDWI grayscale image
contours_mwi = find_wl_contours1(im_mndwi, cloud_mask,
im_ref_buffer)
else:
# use classification to refine threshold and extract the sand/water interface
contours_wi, contours_mwi = find_wl_contours2(
im_ms, im_labels, cloud_mask, buffer_size_pixels,
im_ref_buffer)
except:
print('Could not map shoreline for this image: ' +
filenames[i])
continue
# process water contours into shorelines
shoreline = process_shoreline(contours_mwi, georef, image_epsg,
settings)
# visualise the mapped shorelines, there are two options:
# if settings['check_detection'] = True, shows the detection to the user for accept/reject
# if settings['save_figure'] = True, saves a figure for each mapped shoreline
if settings['check_detection'] or settings['save_figure']:
date = filenames[i][:19]
skip_image = show_detection(im_ms, cloud_mask, im_labels,
shoreline, image_epsg, georef,
settings, date, satname)
# if the user decides to skip the image, continue and do not save the mapped shoreline
if skip_image:
continue
# append to output variables
output_timestamp.append(metadata[satname]['dates'][i])
output_shoreline.append(shoreline)
output_filename.append(filenames[i])
output_cloudcover.append(cloud_cover)
output_geoaccuracy.append(metadata[satname]['acc_georef'][i])
output_idxkeep.append(i)
# create dictionnary of output
output[satname] = {
'dates': output_timestamp,
'shorelines': output_shoreline,
'filename': output_filename,
'cloud_cover': output_cloudcover,
'geoaccuracy': output_geoaccuracy,
'idx': output_idxkeep
}
print('')
# Close figure window if still open
if plt.get_fignums():
plt.close()
# change the format to have one list sorted by date with all the shorelines (easier to use)
output = SDS_tools.merge_output(output)
# save outputput structure as output.pkl
filepath = os.path.join(filepath_data, sitename)
with open(os.path.join(filepath, sitename + '_output.pkl'), 'wb') as f:
pickle.dump(output, f)
# save output into a gdb.GeoDataFrame
gdf = SDS_tools.output_to_gdf(output)
# set projection
gdf.crs = {'init': 'epsg:' + str(settings['output_epsg'])}
# save as geojson
gdf.to_file(os.path.join(filepath, sitename + '_output.geojson'),
driver='GeoJSON',
encoding='utf-8')
return output
def show_detection(im_ms, cloud_mask, im_labels, shoreline, image_epsg, georef,
settings, date, satname):
"""
Shows the detected shoreline to the user for visual quality control. The user can select "keep"
if the shoreline detection is correct or "skip" if it is incorrect.
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_labels: np.array
3D image containing a boolean image for each class in the order (sand, swash, water)
shoreline: np.array
array of points with the X and Y coordinates of the shoreline
image_epsg: int
spatial reference system of the image from which the contours were extracted
georef: np.array
vector of 6 elements [Xtr, Xscale, Xshear, Ytr, Yshear, Yscale]
settings: dict
contains the following fields:
date: string
date at which the image was taken
satname: string
indicates the satname (L5,L7,L8 or S2)
Returns:
-----------
skip_image: boolean
True if the user wants to skip the image, False otherwise.
"""
sitename = settings['inputs']['sitename']
filepath_data = settings['inputs']['filepath']
# subfolder where the .jpg file is stored if the user accepts the shoreline detection
filepath = os.path.join(filepath_data, sitename, 'jpg_files', 'detection')
im_RGB = SDS_preprocess.rescale_image_intensity(im_ms[:, :, [2, 1, 0]],
cloud_mask, 99.9)
# compute classified image
im_class = np.copy(im_RGB)
cmap = cm.get_cmap('tab20c')
colorpalette = cmap(np.arange(0, 13, 1))
colours = np.zeros((3, 4))
colours[0, :] = colorpalette[5]
colours[1, :] = np.array([204 / 255, 1, 1, 1])
colours[2, :] = np.array([0, 91 / 255, 1, 1])
for k in range(0, im_labels.shape[2]):
im_class[im_labels[:, :, k], 0] = colours[k, 0]
im_class[im_labels[:, :, k], 1] = colours[k, 1]
im_class[im_labels[:, :, k], 2] = colours[k, 2]
# compute MNDWI grayscale image
im_mwi = SDS_tools.nd_index(im_ms[:, :, 4], im_ms[:, :, 1], cloud_mask)
# transform world coordinates of shoreline into pixel coordinates
# use try/except in case there are no coordinates to be transformed (shoreline = [])
try:
sl_pix = SDS_tools.convert_world2pix(
SDS_tools.convert_epsg(shoreline, settings['output_epsg'],
image_epsg)[:, [0, 1]], georef)
except:
# if try fails, just add nan into the shoreline vector so the next parts can still run
sl_pix = np.array([[np.nan, np.nan], [np.nan, np.nan]])
if plt.get_fignums():
# get open figure if it exists
fig = plt.gcf()
ax1 = fig.axes[0]
ax2 = fig.axes[1]
ax3 = fig.axes[2]
else:
# else create a new figure
fig = plt.figure()
fig.set_size_inches([12.53, 9.3])
mng = plt.get_current_fig_manager()
mng.window.showMaximized()
# according to the image shape, decide whether it is better to have the images
# in vertical subplots or horizontal subplots
if im_RGB.shape[1] > 2 * im_RGB.shape[0]:
# vertical subplots
gs = gridspec.GridSpec(3, 1)
gs.update(bottom=0.03, top=0.97, left=0.03, right=0.97)
ax1 = fig.add_subplot(gs[0, 0])
ax2 = fig.add_subplot(gs[1, 0])
ax3 = fig.add_subplot(gs[2, 0])
else:
# horizontal subplots
gs = gridspec.GridSpec(1, 3)
gs.update(bottom=0.05, top=0.95, left=0.05, right=0.95)
ax1 = fig.add_subplot(gs[0, 0])
ax2 = fig.add_subplot(gs[0, 1])
ax3 = fig.add_subplot(gs[0, 2])
# change the color of nans to either black (0.0) or white (1.0) or somewhere in between
nan_color = 1.0
im_RGB = np.where(np.isnan(im_RGB), nan_color, im_RGB)
im_class = np.where(np.isnan(im_class), 1.0, im_class)
# create image 1 (RGB)
ax1.imshow(im_RGB)
ax1.plot(sl_pix[:, 0], sl_pix[:, 1], 'k.', markersize=3)
ax1.axis('off')
ax1.set_title(sitename, fontweight='bold', fontsize=16)
# create image 2 (classification)
ax2.imshow(im_class)
ax2.plot(sl_pix[:, 0], sl_pix[:, 1], 'k.', markersize=3)
ax2.axis('off')
orange_patch = mpatches.Patch(color=colours[0, :], label='sand')
white_patch = mpatches.Patch(color=colours[1, :], label='whitewater')
blue_patch = mpatches.Patch(color=colours[2, :], label='water')
black_line = mlines.Line2D([], [],
color='k',
linestyle='-',
label='shoreline')
ax2.legend(handles=[orange_patch, white_patch, blue_patch, black_line],
bbox_to_anchor=(1, 0.5),
fontsize=10)
ax2.set_title(date, fontweight='bold', fontsize=16)
# create image 3 (MNDWI)
ax3.imshow(im_mwi, cmap='bwr')
ax3.plot(sl_pix[:, 0], sl_pix[:, 1], 'k.', markersize=3)
ax3.axis('off')
ax3.set_title(satname, fontweight='bold', fontsize=16)
# additional options
# ax1.set_anchor('W')
# ax2.set_anchor('W')
# cb = plt.colorbar()
# cb.ax.tick_params(labelsize=10)
# cb.set_label('MNDWI values')
# ax3.set_anchor('W')
# if check_detection is True, let user manually accept/reject the images
skip_image = False
if settings['check_detection']:
# set a key event to accept/reject the detections (see https://stackoverflow.com/a/15033071)
# this variable needs to be immuatable so we can access it after the keypress event
key_event = {}
def press(event):
# store what key was pressed in the dictionary
key_event['pressed'] = event.key
# let the user press a key, right arrow to keep the image, left arrow to skip it
# to break the loop the user can press 'escape'
while True:
btn_keep = plt.text(1.1,
0.9,
'keep ⇨',
size=12,
ha="right",
va="top",
transform=ax1.transAxes,
bbox=dict(boxstyle="square", ec='k', fc='w'))
btn_skip = plt.text(-0.1,
0.9,
'⇦ skip',
size=12,
ha="left",
va="top",
transform=ax1.transAxes,
bbox=dict(boxstyle="square", ec='k', fc='w'))
btn_esc = plt.text(0.5,
0,
'<esc> to quit',
size=12,
ha="center",
va="top",
transform=ax1.transAxes,
bbox=dict(boxstyle="square", ec='k', fc='w'))
plt.draw()
fig.canvas.mpl_connect('key_press_event', press)
plt.waitforbuttonpress()
# after button is pressed, remove the buttons
btn_skip.remove()
btn_keep.remove()
btn_esc.remove()
# keep/skip image according to the pressed key, 'escape' to break the loop
if key_event.get('pressed') == 'right':
skip_image = False
break
elif key_event.get('pressed') == 'left':
skip_image = True
break
elif key_event.get('pressed') == 'escape':
plt.close()
raise StopIteration(
'User cancelled checking shoreline detection')
else:
plt.waitforbuttonpress()
# if save_figure is True, save a .jpg under /jpg_files/detection
if settings['save_figure'] and not skip_image:
fig.savefig(os.path.join(filepath, date + '_' + satname + '.jpg'),
dpi=200)
# Don't close the figure window, but remove all axes and settings, ready for next plot
for ax in fig.axes:
ax.clear()
return skip_image
def find_wl_contours2(im_ms, im_labels, cloud_mask, buffer_size,
im_ref_buffer):
"""
New robust method for extracting shorelines. Incorporates the classification component to
refine the treshold and make it specific to the sand/water interface.
KV WRL 2018
Arguments:
-----------
im_ms: np.array
RGB + downsampled NIR and SWIR
im_labels: np.array
3D image containing a boolean image for each class in the order (sand, swash, water)
cloud_mask: np.array
2D cloud mask with True where cloud pixels are
buffer_size: int
size of the buffer around the sandy beach over which the pixels are considered in the
thresholding algorithm.
im_ref_buffer: np.array
Binary image containing a buffer around the reference shoreline
Returns: -----------
contours_wi: list of np.arrays
contains the (row,column) coordinates of the contour lines extracted from the
NDWI (Normalized Difference Water Index) image
contours_mwi: list of np.arrays
contains the (row,column) coordinates of the contour lines extracted from the
MNDWI (Modified Normalized Difference Water Index) image
"""
nrows = cloud_mask.shape[0]
ncols = cloud_mask.shape[1]
# calculate Normalized Difference Modified Water Index (SWIR - G)
im_mwi = SDS_tools.nd_index(im_ms[:, :, 4], im_ms[:, :, 1], cloud_mask)
# calculate Normalized Difference Modified Water Index (NIR - G)
im_wi = SDS_tools.nd_index(im_ms[:, :, 3], im_ms[:, :, 1], cloud_mask)
# stack indices together
im_ind = np.stack((im_wi, im_mwi), axis=-1)
vec_ind = im_ind.reshape(nrows * ncols, 2)
# reshape labels into vectors
vec_sand = im_labels[:, :, 0].reshape(ncols * nrows)
vec_water = im_labels[:, :, 2].reshape(ncols * nrows)
# create a buffer around the sandy beach
se = morphology.disk(buffer_size)
im_buffer = morphology.binary_dilation(im_labels[:, :, 0], se)
vec_buffer = im_buffer.reshape(nrows * ncols)
# select water/sand/swash pixels that are within the buffer
int_water = vec_ind[np.logical_and(vec_buffer, vec_water), :]
int_sand = vec_ind[np.logical_and(vec_buffer, vec_sand), :]
# make sure both classes have the same number of pixels before thresholding
if len(int_water) > 0 and len(int_sand) > 0:
if np.argmin([int_sand.shape[0], int_water.shape[0]]) == 1:
int_sand = int_sand[np.random.choice(
int_sand.shape[0], int_water.shape[0], replace=False), :]
else:
int_water = int_water[np.random.choice(
int_water.shape[0], int_sand.shape[0], replace=False), :]
# threshold the sand/water intensities
int_all = np.append(int_water, int_sand, axis=0)
t_mwi = filters.threshold_otsu(int_all[:, 0])
t_wi = filters.threshold_otsu(int_all[:, 1])
# find contour with MS algorithm
im_wi_buffer = np.copy(im_wi)
im_wi_buffer[~im_ref_buffer] = np.nan
im_mwi_buffer = np.copy(im_mwi)
im_mwi_buffer[~im_ref_buffer] = np.nan
contours_wi = measure.find_contours(im_wi_buffer, t_wi)
contours_mwi = measure.find_contours(im_mwi_buffer, t_mwi)
# remove contour points that are NaNs (around clouds)
contours = contours_wi
contours_nonans = []
for k in range(len(contours)):
if np.any(np.isnan(contours[k])):
index_nan = np.where(np.isnan(contours[k]))[0]
contours_temp = np.delete(contours[k], index_nan, axis=0)
if len(contours_temp) > 1:
contours_nonans.append(contours_temp)
else:
contours_nonans.append(contours[k])
contours_wi = contours_nonans
# repeat for MNDWI contours
contours = contours_mwi
contours_nonans = []
for k in range(len(contours)):
if np.any(np.isnan(contours[k])):
index_nan = np.where(np.isnan(contours[k]))[0]
contours_temp = np.delete(contours[k], index_nan, axis=0)
if len(contours_temp) > 1:
contours_nonans.append(contours_temp)
else:
contours_nonans.append(contours[k])
contours_mwi = contours_nonans
return contours_wi, contours_mwi
def label_images(metadata,settings):
"""
Load satellite images and interactively label different classes (hard-coded)
KV WRL 2019
Arguments:
-----------
metadata: dict
contains all the information about the satellite images that were downloaded
settings: dict with the following keys
'cloud_thresh': float
value between 0 and 1 indicating the maximum cloud fraction in
the cropped image that is accepted
'cloud_mask_issue': boolean
True if there is an issue with the cloud mask and sand pixels
are erroneously being masked on the images
'labels': dict
list of label names (key) and label numbers (value) for each class
'flood_fill': boolean
True to use the flood_fill functionality when labelling sand pixels
'tolerance': float
tolerance value for flood fill when labelling the sand pixels
'filepath_train': str
directory in which to save the labelled data
'inputs': dict
input parameters (sitename, filepath, polygon, dates, sat_list)
Returns:
-----------
Stores the labelled data in the specified directory
"""
filepath_train = settings['filepath_train']
# initialize figure
fig,ax = plt.subplots(1,1,figsize=[17,10], tight_layout=True,sharex=True,
sharey=True)
mng = plt.get_current_fig_manager()
mng.window.showMaximized()
# loop through satellites
for satname in metadata.keys():
filepath = SDS_tools.get_filepath(settings['inputs'],satname)
filenames = metadata[satname]['filenames']
# loop through images
for i in range(len(filenames)):
# image filename
fn = SDS_tools.get_filenames(filenames[i],filepath, satname)
# read and preprocess image
im_ms, georef, cloud_mask, im_extra, im_QA, im_nodata = SDS_preprocess.preprocess_single(fn, satname, settings['cloud_mask_issue'])
# compute cloud_cover percentage (with no data pixels)
cloud_cover_combined = np.divide(sum(sum(cloud_mask.astype(int))),
(cloud_mask.shape[0]*cloud_mask.shape[1]))
if cloud_cover_combined > 0.99: # if 99% of cloudy pixels in image skip
continue
# remove no data pixels from the cloud mask (for example L7 bands of no data should not be accounted for)
cloud_mask_adv = np.logical_xor(cloud_mask, im_nodata)
# compute updated cloud cover percentage (without no data pixels)
cloud_cover = np.divide(sum(sum(cloud_mask_adv.astype(int))),
(sum(sum((~im_nodata).astype(int)))))
# skip image if cloud cover is above threshold
if cloud_cover > settings['cloud_thresh'] or cloud_cover == 1:
continue
# get individual RGB image
im_RGB = SDS_preprocess.rescale_image_intensity(im_ms[:,:,[2,1,0]], cloud_mask, 99.9)
im_NDVI = SDS_tools.nd_index(im_ms[:,:,3], im_ms[:,:,2], cloud_mask)
im_NDWI = SDS_tools.nd_index(im_ms[:,:,3], im_ms[:,:,1], cloud_mask)
# initialise labels
im_viz = im_RGB.copy()
im_labels = np.zeros([im_RGB.shape[0],im_RGB.shape[1]])
# show RGB image
ax.axis('off')
ax.imshow(im_RGB)
implot = ax.imshow(im_viz, alpha=0.6)
filename = filenames[i][:filenames[i].find('.')][:-4]
ax.set_title(filename)
##############################################################
# select image to label
##############################################################
# set a key event to accept/reject the detections (see https://stackoverflow.com/a/15033071)
# this variable needs to be immuatable so we can access it after the keypress event
key_event = {}
def press(event):
# store what key was pressed in the dictionary
key_event['pressed'] = event.key
# let the user press a key, right arrow to keep the image, left arrow to skip it
# to break the loop the user can press 'escape'
while True:
btn_keep = ax.text(1.1, 0.9, 'keep ⇨', size=12, ha="right", va="top",
transform=ax.transAxes,
bbox=dict(boxstyle="square", ec='k',fc='w'))
btn_skip = ax.text(-0.1, 0.9, '⇦ skip', size=12, ha="left", va="top",
transform=ax.transAxes,
bbox=dict(boxstyle="square", ec='k',fc='w'))
btn_esc = ax.text(0.5, 0, '<esc> to quit', size=12, ha="center", va="top",
transform=ax.transAxes,
bbox=dict(boxstyle="square", ec='k',fc='w'))
fig.canvas.draw_idle()
fig.canvas.mpl_connect('key_press_event', press)
plt.waitforbuttonpress()
# after button is pressed, remove the buttons
btn_skip.remove()
btn_keep.remove()
btn_esc.remove()
# keep/skip image according to the pressed key, 'escape' to break the loop
if key_event.get('pressed') == 'right':
skip_image = False
break
elif key_event.get('pressed') == 'left':
skip_image = True
break
elif key_event.get('pressed') == 'escape':
plt.close()
raise StopIteration('User cancelled labelling images')
else:
plt.waitforbuttonpress()
# if user decided to skip show the next image
if skip_image:
ax.clear()
continue
# otherwise label this image
else:
##############################################################
# digitize sandy pixels
##############################################################
ax.set_title('Click on SAND pixels (flood fill activated, tolerance = %.2f)\nwhen finished press <Enter>'%settings['tolerance'])
# create erase button, if you click there it delets the last selection
btn_erase = ax.text(im_ms.shape[1], 0, 'Erase', size=20, ha='right', va='top',
bbox=dict(boxstyle="square", ec='k',fc='w'))
fig.canvas.draw_idle()
color_sand = settings['colors']['sand']
sand_pixels = []
while 1:
seed = ginput(n=1, timeout=0, show_clicks=True)
# if empty break the loop and go to next label
if len(seed) == 0:
break
else:
# round to pixel location
seed = np.round(seed[0]).astype(int)
# if user clicks on erase, delete the last selection
if seed[0] > 0.95*im_ms.shape[1] and seed[1] < 0.05*im_ms.shape[0]:
if len(sand_pixels) > 0:
im_labels[sand_pixels[-1]] = 0
for k in range(im_viz.shape[2]):
im_viz[sand_pixels[-1],k] = im_RGB[sand_pixels[-1],k]
implot.set_data(im_viz)
fig.canvas.draw_idle()
del sand_pixels[-1]
# otherwise label the selected sand pixels
else:
# flood fill the NDVI and the NDWI
fill_NDVI = flood(im_NDVI, (seed[1],seed[0]), tolerance=settings['tolerance'])
fill_NDWI = flood(im_NDWI, (seed[1],seed[0]), tolerance=settings['tolerance'])
# compute the intersection of the two masks
fill_sand = np.logical_and(fill_NDVI, fill_NDWI)
im_labels[fill_sand] = settings['labels']['sand']
sand_pixels.append(fill_sand)
# show the labelled pixels
for k in range(im_viz.shape[2]):
im_viz[im_labels==settings['labels']['sand'],k] = color_sand[k]
implot.set_data(im_viz)
fig.canvas.draw_idle()
##############################################################
# digitize white-water pixels
##############################################################
color_ww = settings['colors']['white-water']
ax.set_title('Click on individual WHITE-WATER pixels (no flood fill)\nwhen finished press <Enter>')
fig.canvas.draw_idle()
ww_pixels = []
while 1:
seed = ginput(n=1, timeout=0, show_clicks=True)
# if empty break the loop and go to next label
if len(seed) == 0:
break
else:
# round to pixel location
seed = np.round(seed[0]).astype(int)
# if user clicks on erase, delete the last labelled pixels
if seed[0] > 0.95*im_ms.shape[1] and seed[1] < 0.05*im_ms.shape[0]:
if len(ww_pixels) > 0:
im_labels[ww_pixels[-1][1],ww_pixels[-1][0]] = 0
for k in range(im_viz.shape[2]):
im_viz[ww_pixels[-1][1],ww_pixels[-1][0],k] = im_RGB[ww_pixels[-1][1],ww_pixels[-1][0],k]
implot.set_data(im_viz)
fig.canvas.draw_idle()
del ww_pixels[-1]
else:
im_labels[seed[1],seed[0]] = settings['labels']['white-water']
for k in range(im_viz.shape[2]):
im_viz[seed[1],seed[0],k] = color_ww[k]
implot.set_data(im_viz)
fig.canvas.draw_idle()
ww_pixels.append(seed)
im_sand_ww = im_viz.copy()
btn_erase.set(text='<Esc> to Erase', fontsize=12)
##############################################################
# digitize water pixels (with lassos)
##############################################################
color_water = settings['colors']['water']
ax.set_title('Click and hold to draw lassos and select WATER pixels\nwhen finished press <Enter>')
fig.canvas.draw_idle()
selector_water = SelectFromImage(ax, implot, color_water)
key_event = {}
while True:
fig.canvas.draw_idle()
fig.canvas.mpl_connect('key_press_event', press)
plt.waitforbuttonpress()
if key_event.get('pressed') == 'enter':
selector_water.disconnect()
break
elif key_event.get('pressed') == 'escape':
selector_water.array = im_sand_ww
implot.set_data(selector_water.array)
fig.canvas.draw_idle()
selector_water.implot = implot
selector_water.im_bool = np.zeros((selector_water.array.shape[0], selector_water.array.shape[1]))
selector_water.ind=[]
# update im_viz and im_labels
im_viz = selector_water.array
selector_water.im_bool = selector_water.im_bool.astype(bool)
im_labels[selector_water.im_bool] = settings['labels']['water']
im_sand_ww_water = im_viz.copy()
##############################################################
# digitize land pixels (with lassos)
##############################################################
color_land = settings['colors']['other land features']
ax.set_title('Click and hold to draw lassos and select OTHER LAND pixels\nwhen finished press <Enter>')
fig.canvas.draw_idle()
selector_land = SelectFromImage(ax, implot, color_land)
key_event = {}
while True:
fig.canvas.draw_idle()
fig.canvas.mpl_connect('key_press_event', press)
plt.waitforbuttonpress()
if key_event.get('pressed') == 'enter':
selector_land.disconnect()
break
elif key_event.get('pressed') == 'escape':
selector_land.array = im_sand_ww_water
implot.set_data(selector_land.array)
fig.canvas.draw_idle()
selector_land.implot = implot
selector_land.im_bool = np.zeros((selector_land.array.shape[0], selector_land.array.shape[1]))
selector_land.ind=[]
# update im_viz and im_labels
im_viz = selector_land.array
selector_land.im_bool = selector_land.im_bool.astype(bool)
im_labels[selector_land.im_bool] = settings['labels']['other land features']
# save labelled image
ax.set_title(filename)
fig.canvas.draw_idle()
fp = os.path.join(filepath_train,settings['inputs']['sitename'])
if not os.path.exists(fp):
os.makedirs(fp)
fig.savefig(os.path.join(fp,filename+'.jpg'), dpi=150)
ax.clear()
# save labels and features
features = dict([])
for key in settings['labels'].keys():
im_bool = im_labels == settings['labels'][key]
features[key] = SDS_shoreline.calculate_features(im_ms, cloud_mask, im_bool)
training_data = {'labels':im_labels, 'features':features, 'label_ids':settings['labels']}
with open(os.path.join(fp, filename + '.pkl'), 'wb') as f:
pickle.dump(training_data,f)
# close figure when finished
plt.close(fig)
def evaluate_classifier(classifier, metadata, settings):
"""
Apply the image classifier to all the images and save the classified images.
KV WRL 2019
Arguments:
-----------
classifier: joblib object
classifier model to be used for image classification
metadata: dict
contains all the information about the satellite images that were downloaded
settings: dict with the following keys
'inputs': dict
input parameters (sitename, filepath, polygon, dates, sat_list)
'cloud_thresh': float
value between 0 and 1 indicating the maximum cloud fraction in
the cropped image that is accepted
'cloud_mask_issue': boolean
True if there is an issue with the cloud mask and sand pixels
are erroneously being masked on the images
'output_epsg': int
output spatial reference system as EPSG code
'buffer_size': int
size of the buffer (m) around the sandy pixels over which the pixels
are considered in the thresholding algorithm
'min_beach_area': int
minimum allowable object area (in metres^2) for the class 'sand',
the area is converted to number of connected pixels
'min_length_sl': int
minimum length (in metres) of shoreline contour to be valid
Returns:
-----------
Saves .jpg images with the output of the classification in the folder ./detection
"""
# create folder called evaluation
fp = os.path.join(os.getcwd(), 'evaluation')
if not os.path.exists(fp):
os.makedirs(fp)
# initialize figure (not interactive)
plt.ioff()
fig,ax = plt.subplots(1,2,figsize=[17,10],sharex=True, sharey=True,
constrained_layout=True)
# create colormap for labels
cmap = cm.get_cmap('tab20c')
colorpalette = cmap(np.arange(0,13,1))
colours = np.zeros((3,4))
colours[0,:] = colorpalette[5]
colours[1,:] = np.array([204/255,1,1,1])
colours[2,:] = np.array([0,91/255,1,1])
# loop through satellites
for satname in metadata.keys():
filepath = SDS_tools.get_filepath(settings['inputs'],satname)
filenames = metadata[satname]['filenames']
# load classifiers and
if satname in ['L5','L7','L8']:
pixel_size = 15
elif satname == 'S2':
pixel_size = 10
# convert settings['min_beach_area'] and settings['buffer_size'] from metres to pixels
buffer_size_pixels = np.ceil(settings['buffer_size']/pixel_size)
min_beach_area_pixels = np.ceil(settings['min_beach_area']/pixel_size**2)
# loop through images
for i in range(len(filenames)):
# image filename
fn = SDS_tools.get_filenames(filenames[i],filepath, satname)
# read and preprocess image
im_ms, georef, cloud_mask, im_extra, im_QA, im_nodata = SDS_preprocess.preprocess_single(fn, satname, settings['cloud_mask_issue'])
image_epsg = metadata[satname]['epsg'][i]
# compute cloud_cover percentage (with no data pixels)
cloud_cover_combined = np.divide(sum(sum(cloud_mask.astype(int))),
(cloud_mask.shape[0]*cloud_mask.shape[1]))
if cloud_cover_combined > 0.99: # if 99% of cloudy pixels in image skip
continue
# remove no data pixels from the cloud mask (for example L7 bands of no data should not be accounted for)
cloud_mask_adv = np.logical_xor(cloud_mask, im_nodata)
# compute updated cloud cover percentage (without no data pixels)
cloud_cover = np.divide(sum(sum(cloud_mask_adv.astype(int))),
(sum(sum((~im_nodata).astype(int)))))
# skip image if cloud cover is above threshold
if cloud_cover > settings['cloud_thresh']:
continue
# calculate a buffer around the reference shoreline (if any has been digitised)
im_ref_buffer = SDS_shoreline.create_shoreline_buffer(cloud_mask.shape, georef, image_epsg,
pixel_size, settings)
# classify image in 4 classes (sand, whitewater, water, other) with NN classifier
im_classif, im_labels = SDS_shoreline.classify_image_NN(im_ms, im_extra, cloud_mask,
min_beach_area_pixels, classifier)
# there are two options to map the contours:
# if there are pixels in the 'sand' class --> use find_wl_contours2 (enhanced)
# otherwise use find_wl_contours2 (traditional)
try: # use try/except structure for long runs
if sum(sum(im_labels[:,:,0])) < 10 :
# compute MNDWI image (SWIR-G)
im_mndwi = SDS_tools.nd_index(im_ms[:,:,4], im_ms[:,:,1], cloud_mask)
# find water contours on MNDWI grayscale image
contours_mwi, t_mndwi = SDS_shoreline.find_wl_contours1(im_mndwi, cloud_mask, im_ref_buffer)
else:
# use classification to refine threshold and extract the sand/water interface
contours_mwi, t_mndwi = SDS_shoreline.find_wl_contours2(im_ms, im_labels,
cloud_mask, buffer_size_pixels, im_ref_buffer)
except:
print('Could not map shoreline for this image: ' + filenames[i])
continue
# process the water contours into a shoreline
shoreline = SDS_shoreline.process_shoreline(contours_mwi, cloud_mask, georef, image_epsg, settings)
try:
sl_pix = SDS_tools.convert_world2pix(SDS_tools.convert_epsg(shoreline,
settings['output_epsg'],
image_epsg)[:,[0,1]], georef)
except:
# if try fails, just add nan into the shoreline vector so the next parts can still run
sl_pix = np.array([[np.nan, np.nan],[np.nan, np.nan]])
# make a plot
im_RGB = SDS_preprocess.rescale_image_intensity(im_ms[:,:,[2,1,0]], cloud_mask, 99.9)
# create classified image
im_class = np.copy(im_RGB)
for k in range(0,im_labels.shape[2]):
im_class[im_labels[:,:,k],0] = colours[k,0]
im_class[im_labels[:,:,k],1] = colours[k,1]
im_class[im_labels[:,:,k],2] = colours[k,2]
# show images
ax[0].imshow(im_RGB)
ax[1].imshow(im_RGB)
ax[1].imshow(im_class, alpha=0.5)
ax[0].axis('off')
ax[1].axis('off')
filename = filenames[i][:filenames[i].find('.')][:-4]
ax[0].set_title(filename)
ax[0].plot(sl_pix[:,0], sl_pix[:,1], 'k.', markersize=3)
ax[1].plot(sl_pix[:,0], sl_pix[:,1], 'k.', markersize=3)
# save figure
fig.savefig(os.path.join(fp,settings['inputs']['sitename'] + filename[:19] +'.jpg'), dpi=150)
# clear axes
for cax in fig.axes:
cax.clear()
# close the figure at the end
plt.close()
def find_wl_contours2(im_ms, im_labels, cloud_mask, buffer_size, im_ref_buffer,
dirty_hack_flag):
"""
New robust method for extracting shorelines. Incorporates the classification
component to refine the treshold and make it specific to the sand/water interface.
KV WRL 2018
Arguments:
-----------
im_ms: np.array
RGB + downsampled NIR and SWIR
im_labels: np.array
3D image containing a boolean image for each class in the order (sand, swash, water)
cloud_mask: np.array
2D cloud mask with True where cloud pixels are
buffer_size: int
size of the buffer around the sandy beach over which the pixels are considered in the
thresholding algorithm.
im_ref_buffer: np.array
binary image containing a buffer around the reference shoreline
Returns:
-----------
contours_wi: list of np.arrays
contains the coordinates of the contour lines extracted from the
NDWI (Normalized Difference Water Index) image
contours_mwi: list of np.arrays
contains the coordinates of the contour lines extracted from the
MNDWI (Modified Normalized Difference Water Index) image
"""
nrows = cloud_mask.shape[0]
ncols = cloud_mask.shape[1]
# calculate Normalized Difference Modified Water Index (SWIR - G)
im_mwi = SDS_tools.nd_index(im_ms[:, :, 4], im_ms[:, :, 1], cloud_mask)
# calculate Normalized Difference Modified Water Index (NIR - G)
im_wi = SDS_tools.nd_index(im_ms[:, :, 3], im_ms[:, :, 1], cloud_mask)
# stack indices together
im_ind = np.stack((im_wi, im_mwi), axis=-1)
vec_ind = im_ind.reshape(nrows * ncols, 2)
# print("The flag for dirty hack: ", dirty_hack_flag)
if dirty_hack_flag:
print("I am doing the dirty hack!")
##### <<<<<<<<<<<<<<<<<< DIRTYHACK >>>>>>>>>>>>>>>>>>>>>>>> ####
# Find a better way to do it!
# Update the indexes:
# If all the indexes are false (without a lable, i.e others)
# add the index true for sand.
# If the index for white water is true, automatically update
# update the index to water index.
for array in np.ndindex(im_labels.shape[:2]):
i, j = array
if np.any(im_labels[array] == True):
if im_labels[i, j, 1] == True:
# print("Check if it is true:", im_labels[i,j,1])
# print("Before the water update:", im_labels[i,j,2])
im_labels[i, j, 2] = True
# print("After the water update:", im_labels[i,j,2])
else:
# print("Before", im_labels[array] )
# print("Checj if it is the first element: ", im_labels[i,j,0])
im_labels[i, j, 0] = True
# print("After", im_labels[array])
pass
pass
##### <<<<<<<<<<<<<<<<<<< DIRTYHACK >>>>>>>>>>>>>>>>>>>>>>>> ####
pass
# reshape labels into vectors
vec_sand = im_labels[:, :, 0].reshape(ncols * nrows)
vec_water = im_labels[:, :, 2].reshape(ncols * nrows)
# create a buffer around the sandy beach
se = morphology.disk(buffer_size)
im_buffer = morphology.binary_dilation(im_labels[:, :, 0], se)
vec_buffer = im_buffer.reshape(nrows * ncols)
# select water/sand/swash pixels that are within the buffer
int_water = vec_ind[np.logical_and(vec_buffer, vec_water), :]
int_sand = vec_ind[np.logical_and(vec_buffer, vec_sand), :]
# make sure both classes have the same number of pixels before thresholding
if len(int_water) > 0 and len(int_sand) > 0:
if np.argmin([int_sand.shape[0], int_water.shape[0]]) == 1:
int_sand = int_sand[np.random.choice(
int_sand.shape[0], int_water.shape[0], replace=False), :]
else:
int_water = int_water[np.random.choice(
int_water.shape[0], int_sand.shape[0], replace=False), :]
# threshold the sand/water intensities
int_all = np.append(int_water, int_sand, axis=0)
t_mwi = filters.threshold_otsu(int_all[:, 0])
t_wi = filters.threshold_otsu(int_all[:, 1])
# find contour with MS algorithm
im_wi_buffer = np.copy(im_wi)
im_wi_buffer[~im_ref_buffer] = np.nan
im_mwi_buffer = np.copy(im_mwi)
im_mwi_buffer[~im_ref_buffer] = np.nan
contours_wi = measure.find_contours(im_wi_buffer, t_wi)
contours_mwi = measure.find_contours(im_mwi_buffer, t_mwi)
# remove contour points that are NaNs (around clouds)
contours = contours_wi
contours_nonans = []
for k in range(len(contours)):
if np.any(np.isnan(contours[k])):
index_nan = np.where(np.isnan(contours[k]))[0]
contours_temp = np.delete(contours[k], index_nan, axis=0)
if len(contours_temp) > 1:
contours_nonans.append(contours_temp)
else:
contours_nonans.append(contours[k])
contours_wi = contours_nonans
# repeat for MNDWI contours
contours = contours_mwi
contours_nonans = []
for k in range(len(contours)):
if np.any(np.isnan(contours[k])):
index_nan = np.where(np.isnan(contours[k]))[0]
contours_temp = np.delete(contours[k], index_nan, axis=0)
if len(contours_temp) > 1:
contours_nonans.append(contours_temp)
else:
contours_nonans.append(contours[k])
contours_mwi = contours_nonans
return contours_wi, contours_mwi
def adjust_detection(im_ms, cloud_mask, im_labels, im_ref_buffer, image_epsg, georef,
settings, date, satname, buffer_size_pixels):
"""
Advanced version of show detection where the user can adjust the detected
shorelines with a slide bar.
KV WRL 2020
Arguments:
-----------
im_ms: np.array
RGB + downsampled NIR and SWIR
cloud_mask: np.array
2D cloud mask with True where cloud pixels are
im_labels: np.array
3D image containing a boolean image for each class in the order (sand, swash, water)
im_ref_buffer: np.array
Binary image containing a buffer around the reference shoreline
image_epsg: int
spatial reference system of the image from which the contours were extracted
georef: np.array
vector of 6 elements [Xtr, Xscale, Xshear, Ytr, Yshear, Yscale]
date: string
date at which the image was taken
satname: string
indicates the satname (L5,L7,L8 or S2)
buffer_size_pixels: int
buffer_size converted to number of pixels
settings: dict with the following keys
'inputs': dict
input parameters (sitename, filepath, polygon, dates, sat_list)
'output_epsg': int
output spatial reference system as EPSG code
'save_figure': bool
if True, saves a -jpg file for each mapped shoreline
Returns:
-----------
skip_image: boolean
True if the user wants to skip the image, False otherwise
shoreline: np.array
array of points with the X and Y coordinates of the shoreline
t_mndwi: float
value of the MNDWI threshold used to map the shoreline
"""
sitename = settings['inputs']['sitename']
filepath_data = settings['inputs']['filepath']
# subfolder where the .jpg file is stored if the user accepts the shoreline detection
filepath = os.path.join(filepath_data, sitename, 'jpg_files', 'detection')
# format date
date_str = datetime.strptime(date,'%Y-%m-%d-%H-%M-%S').strftime('%Y-%m-%d %H:%M:%S')
im_RGB = SDS_preprocess.rescale_image_intensity(im_ms[:,:,[2,1,0]], cloud_mask, 99.9)
# compute classified image
im_class = np.copy(im_RGB)
cmap = cm.get_cmap('tab20c')
colorpalette = cmap(np.arange(0,13,1))
colours = np.zeros((3,4))
colours[0,:] = colorpalette[5]
colours[1,:] = np.array([204/255,1,1,1])
colours[2,:] = np.array([0,91/255,1,1])
for k in range(0,im_labels.shape[2]):
im_class[im_labels[:,:,k],0] = colours[k,0]
im_class[im_labels[:,:,k],1] = colours[k,1]
im_class[im_labels[:,:,k],2] = colours[k,2]
# compute MNDWI grayscale image
im_mndwi = SDS_tools.nd_index(im_ms[:,:,4], im_ms[:,:,1], cloud_mask)
# buffer MNDWI using reference shoreline
im_mndwi_buffer = np.copy(im_mndwi)
im_mndwi_buffer[~im_ref_buffer] = np.nan
# get MNDWI pixel intensity in each class (for histogram plot)
int_sand = im_mndwi[im_labels[:,:,0]]
int_ww = im_mndwi[im_labels[:,:,1]]
int_water = im_mndwi[im_labels[:,:,2]]
labels_other = np.logical_and(np.logical_and(~im_labels[:,:,0],~im_labels[:,:,1]),~im_labels[:,:,2])
int_other = im_mndwi[labels_other]
# create figure
if plt.get_fignums():
# if it exists, open the figure
fig = plt.gcf()
ax1 = fig.axes[0]
ax2 = fig.axes[1]
ax3 = fig.axes[2]
ax4 = fig.axes[3]
else:
# else create a new figure
fig = plt.figure()
fig.set_size_inches([18, 9])
mng = plt.get_current_fig_manager()
mng.window.showMaximized()
gs = gridspec.GridSpec(2, 3, height_ratios=[4,1])
gs.update(bottom=0.05, top=0.95, left=0.03, right=0.97)
ax1 = fig.add_subplot(gs[0,0])
ax2 = fig.add_subplot(gs[0,1], sharex=ax1, sharey=ax1)
ax3 = fig.add_subplot(gs[0,2], sharex=ax1, sharey=ax1)
ax4 = fig.add_subplot(gs[1,:])
##########################################################################
# to do: rotate image if too wide
##########################################################################
# change the color of nans to either black (0.0) or white (1.0) or somewhere in between
nan_color = 1.0
im_RGB = np.where(np.isnan(im_RGB), nan_color, im_RGB)
im_class = np.where(np.isnan(im_class), 1.0, im_class)
# plot image 1 (RGB)
ax1.imshow(im_RGB)
ax1.axis('off')
ax1.set_title('%s - %s'%(sitename, satname), fontsize=12)
# plot image 2 (classification)
ax2.imshow(im_class)
ax2.axis('off')
orange_patch = mpatches.Patch(color=colours[0,:], label='sand')
white_patch = mpatches.Patch(color=colours[1,:], label='whitewater')
blue_patch = mpatches.Patch(color=colours[2,:], label='water')
black_line = mlines.Line2D([],[],color='k',linestyle='-', label='shoreline')
ax2.legend(handles=[orange_patch,white_patch,blue_patch, black_line],
bbox_to_anchor=(1.1, 0.5), fontsize=10)
ax2.set_title(date_str, fontsize=12)
# plot image 3 (MNDWI)
ax3.imshow(im_mndwi, cmap='bwr')
ax3.axis('off')
ax3.set_title('MNDWI', fontsize=12)
# plot histogram of MNDWI values
binwidth = 0.01
ax4.set_facecolor('0.75')
ax4.yaxis.grid(color='w', linestyle='--', linewidth=0.5)
ax4.set(ylabel='PDF',yticklabels=[], xlim=[-1,1])
if len(int_sand) > 0 and sum(~np.isnan(int_sand)) > 0:
bins = np.arange(np.nanmin(int_sand), np.nanmax(int_sand) + binwidth, binwidth)
ax4.hist(int_sand, bins=bins, density=True, color=colours[0,:], label='sand')
if len(int_ww) > 0 and sum(~np.isnan(int_ww)) > 0:
bins = np.arange(np.nanmin(int_ww), np.nanmax(int_ww) + binwidth, binwidth)
ax4.hist(int_ww, bins=bins, density=True, color=colours[1,:], label='whitewater', alpha=0.75)
if len(int_water) > 0 and sum(~np.isnan(int_water)) > 0:
bins = np.arange(np.nanmin(int_water), np.nanmax(int_water) + binwidth, binwidth)
ax4.hist(int_water, bins=bins, density=True, color=colours[2,:], label='water', alpha=0.75)
if len(int_other) > 0 and sum(~np.isnan(int_other)) > 0:
bins = np.arange(np.nanmin(int_other), np.nanmax(int_other) + binwidth, binwidth)
ax4.hist(int_other, bins=bins, density=True, color='C4', label='other', alpha=0.5)
# automatically map the shoreline based on the classifier if enough sand pixels
try:
if sum(sum(im_labels[:,:,0])) > 10:
# use classification to refine threshold and extract the sand/water interface
contours_mndwi, t_mndwi = find_wl_contours2(im_ms, im_labels, cloud_mask,
buffer_size_pixels, im_ref_buffer)
else:
# find water contours on MNDWI grayscale image
contours_mndwi, t_mndwi = find_wl_contours1(im_mndwi, cloud_mask, im_ref_buffer)
except:
print('Could not map shoreline so image was skipped')
# clear axes and return skip_image=True, so that image is skipped above
for ax in fig.axes:
ax.clear()
return True,[],[]
# process the water contours into a shoreline
shoreline = process_shoreline(contours_mndwi, cloud_mask, georef, image_epsg, settings)
# convert shoreline to pixels
if len(shoreline) > 0:
sl_pix = SDS_tools.convert_world2pix(SDS_tools.convert_epsg(shoreline,
settings['output_epsg'],
image_epsg)[:,[0,1]], georef)
else: sl_pix = np.array([[np.nan, np.nan],[np.nan, np.nan]])
# plot the shoreline on the images
sl_plot1 = ax1.plot(sl_pix[:,0], sl_pix[:,1], 'k.', markersize=3)
sl_plot2 = ax2.plot(sl_pix[:,0], sl_pix[:,1], 'k.', markersize=3)
sl_plot3 = ax3.plot(sl_pix[:,0], sl_pix[:,1], 'k.', markersize=3)
t_line = ax4.axvline(x=t_mndwi,ls='--', c='k', lw=1.5, label='threshold')
ax4.legend(loc=1)
plt.draw() # to update the plot
# adjust the threshold manually by letting the user change the threshold
ax4.set_title('Click on the plot below to change the location of the threhsold and adjust the shoreline detection. When finished, press <Enter>')
while True:
# let the user click on the threshold plot
pt = ginput(n=1, show_clicks=True, timeout=-1)
# if a point was clicked
if len(pt) > 0:
# if user clicked somewhere wrong and value is not between -1 and 1
if np.abs(pt[0][0]) >= 1: continue
# update the threshold value
t_mndwi = pt[0][0]
# update the plot
t_line.set_xdata([t_mndwi,t_mndwi])
# map contours with new threshold
contours = measure.find_contours(im_mndwi_buffer, t_mndwi)
# remove contours that contain NaNs (due to cloud pixels in the contour)
contours = process_contours(contours)
# process the water contours into a shoreline
shoreline = process_shoreline(contours, cloud_mask, georef, image_epsg, settings)
# convert shoreline to pixels
if len(shoreline) > 0:
sl_pix = SDS_tools.convert_world2pix(SDS_tools.convert_epsg(shoreline,
settings['output_epsg'],
image_epsg)[:,[0,1]], georef)
else: sl_pix = np.array([[np.nan, np.nan],[np.nan, np.nan]])
# update the plotted shorelines
sl_plot1[0].set_data([sl_pix[:,0], sl_pix[:,1]])
sl_plot2[0].set_data([sl_pix[:,0], sl_pix[:,1]])
sl_plot3[0].set_data([sl_pix[:,0], sl_pix[:,1]])
fig.canvas.draw_idle()
else:
ax4.set_title('MNDWI pixel intensities and threshold')
break
# let user manually accept/reject the image
skip_image = False
# set a key event to accept/reject the detections (see https://stackoverflow.com/a/15033071)
# this variable needs to be immuatable so we can access it after the keypress event
key_event = {}
def press(event):
# store what key was pressed in the dictionary
key_event['pressed'] = event.key
# let the user press a key, right arrow to keep the image, left arrow to skip it
# to break the loop the user can press 'escape'
while True:
btn_keep = plt.text(1.1, 0.9, 'keep ⇨', size=12, ha="right", va="top",
transform=ax1.transAxes,
bbox=dict(boxstyle="square", ec='k',fc='w'))
btn_skip = plt.text(-0.1, 0.9, '⇦ skip', size=12, ha="left", va="top",
transform=ax1.transAxes,
bbox=dict(boxstyle="square", ec='k',fc='w'))
btn_esc = plt.text(0.5, 0, '<esc> to quit', size=12, ha="center", va="top",
transform=ax1.transAxes,
bbox=dict(boxstyle="square", ec='k',fc='w'))
plt.draw()
fig.canvas.mpl_connect('key_press_event', press)
plt.waitforbuttonpress()
# after button is pressed, remove the buttons
btn_skip.remove()
btn_keep.remove()
btn_esc.remove()
# keep/skip image according to the pressed key, 'escape' to break the loop
if key_event.get('pressed') == 'right':
skip_image = False
break
elif key_event.get('pressed') == 'left':
skip_image = True
break
elif key_event.get('pressed') == 'escape':
plt.close()
raise StopIteration('User cancelled checking shoreline detection')
else:
plt.waitforbuttonpress()
# if save_figure is True, save a .jpg under /jpg_files/detection
if settings['save_figure'] and not skip_image:
fig.savefig(os.path.join(filepath, date + '_' + satname + '.jpg'), dpi=150)
# don't close the figure window, but remove all axes and settings, ready for next plot
for ax in fig.axes:
ax.clear()
return skip_image, shoreline, t_mndwi
def extract_shorelines(metadata, settings):
"""
Main function to extract shorelines from satellite images
KV WRL 2018
Arguments:
-----------
metadata: dict
contains all the information about the satellite images that were downloaded
settings: dict with the following keys
'inputs': dict
input parameters (sitename, filepath, polygon, dates, sat_list)
'cloud_thresh': float
value between 0 and 1 indicating the maximum cloud fraction in
the cropped image that is accepted
'cloud_mask_issue': boolean
True if there is an issue with the cloud mask and sand pixels
are erroneously being masked on the images
'buffer_size': int
size of the buffer (m) around the sandy pixels over which the pixels
are considered in the thresholding algorithm
'min_beach_area': int
minimum allowable object area (in metres^2) for the class 'sand',
the area is converted to number of connected pixels
'min_length_sl': int
minimum length (in metres) of shoreline contour to be valid
'sand_color': str
default', 'dark' (for grey/black sand beaches) or 'bright' (for white sand beaches)
'output_epsg': int
output spatial reference system as EPSG code
'check_detection': bool
if True, lets user manually accept/reject the mapped shorelines
'save_figure': bool
if True, saves a -jpg file for each mapped shoreline
'adjust_detection': bool
if True, allows user to manually adjust the detected shoreline
Returns:
-----------
output: dict
contains the extracted shorelines and corresponding dates + metadata
"""
sitename = settings['inputs']['sitename']
filepath_data = settings['inputs']['filepath']
filepath_models = os.path.join(os.getcwd(), 'classification', 'models')
# initialise output structure
output = dict([])
# create a subfolder to store the .jpg images showing the detection
filepath_jpg = os.path.join(filepath_data, sitename, 'jpg_files', 'detection')
if not os.path.exists(filepath_jpg):
os.makedirs(filepath_jpg)
# close all open figures
plt.close('all')
print('Mapping shorelines:')
# loop through satellite list
for satname in metadata.keys():
# get images
filepath = SDS_tools.get_filepath(settings['inputs'],satname)
filenames = metadata[satname]['filenames']
# initialise the output variables
output_timestamp = [] # datetime at which the image was acquired (UTC time)
output_shoreline = [] # vector of shoreline points
output_filename = [] # filename of the images from which the shorelines where derived
output_cloudcover = [] # cloud cover of the images
output_geoaccuracy = []# georeferencing accuracy of the images
output_idxkeep = [] # index that were kept during the analysis (cloudy images are skipped)
output_t_mndwi = [] # MNDWI threshold used to map the shoreline
# load classifiers (if sklearn version above 0.20, learn the new files)
str_new = ''
if not sklearn.__version__[:4] == '0.20':
str_new = '_new'
if satname in ['L5','L7','L8']:
pixel_size = 15
if settings['sand_color'] == 'dark':
clf = joblib.load(os.path.join(filepath_models, 'NN_4classes_Landsat_dark%s.pkl'%str_new))
elif settings['sand_color'] == 'bright':
clf = joblib.load(os.path.join(filepath_models, 'NN_4classes_Landsat_bright%s.pkl'%str_new))
else:
clf = joblib.load(os.path.join(filepath_models, 'NN_4classes_Landsat%s.pkl'%str_new))
elif satname == 'S2':
pixel_size = 10
clf = joblib.load(os.path.join(filepath_models, 'NN_4classes_S2%s.pkl'%str_new))
# convert settings['min_beach_area'] and settings['buffer_size'] from metres to pixels
buffer_size_pixels = np.ceil(settings['buffer_size']/pixel_size)
min_beach_area_pixels = np.ceil(settings['min_beach_area']/pixel_size**2)
# loop through the images
for i in range(len(filenames)):
print('\r%s: %d%%' % (satname,int(((i+1)/len(filenames))*100)), end='')
# get image filename
fn = SDS_tools.get_filenames(filenames[i],filepath, satname)
# preprocess image (cloud mask + pansharpening/downsampling)
im_ms, georef, cloud_mask, im_extra, im_QA, im_nodata = SDS_preprocess.preprocess_single(fn, satname, settings['cloud_mask_issue'])
# get image spatial reference system (epsg code) from metadata dict
image_epsg = metadata[satname]['epsg'][i]
# compute cloud_cover percentage (with no data pixels)
cloud_cover_combined = np.divide(sum(sum(cloud_mask.astype(int))),
(cloud_mask.shape[0]*cloud_mask.shape[1]))
if cloud_cover_combined > 0.99: # if 99% of cloudy pixels in image skip
continue
# remove no data pixels from the cloud mask
# (for example L7 bands of no data should not be accounted for)
cloud_mask_adv = np.logical_xor(cloud_mask, im_nodata)
# compute updated cloud cover percentage (without no data pixels)
cloud_cover = np.divide(sum(sum(cloud_mask_adv.astype(int))),
(cloud_mask.shape[0]*cloud_mask.shape[1]))
# skip image if cloud cover is above user-defined threshold
if cloud_cover > settings['cloud_thresh']:
continue
# calculate a buffer around the reference shoreline (if any has been digitised)
im_ref_buffer = create_shoreline_buffer(cloud_mask.shape, georef, image_epsg,
pixel_size, settings)
# classify image in 4 classes (sand, whitewater, water, other) with NN classifier
im_classif, im_labels = classify_image_NN(im_ms, im_extra, cloud_mask,
min_beach_area_pixels, clf)
# if adjust_detection is True, let the user adjust the detected shoreline
if settings['adjust_detection']:
date = filenames[i][:19]
skip_image, shoreline, t_mndwi = adjust_detection(im_ms, cloud_mask, im_labels,
im_ref_buffer, image_epsg, georef,
settings, date, satname, buffer_size_pixels)
# if the user decides to skip the image, continue and do not save the mapped shoreline
if skip_image:
continue
# otherwise map the contours automatically with one of the two following functions:
# if there are pixels in the 'sand' class --> use find_wl_contours2 (enhanced)
# otherwise use find_wl_contours2 (traditional)
else:
try: # use try/except structure for long runs
if sum(sum(im_labels[:,:,0])) < 10 : # minimum number of sand pixels
# compute MNDWI image (SWIR-G)
im_mndwi = SDS_tools.nd_index(im_ms[:,:,4], im_ms[:,:,1], cloud_mask)
# find water contours on MNDWI grayscale image
contours_mwi, t_mndwi = find_wl_contours1(im_mndwi, cloud_mask, im_ref_buffer)
else:
# use classification to refine threshold and extract the sand/water interface
contours_mwi, t_mndwi = find_wl_contours2(im_ms, im_labels, cloud_mask,
buffer_size_pixels, im_ref_buffer)
except:
print('Could not map shoreline for this image: ' + filenames[i])
continue
# process the water contours into a shoreline
shoreline = process_shoreline(contours_mwi, cloud_mask, georef, image_epsg, settings)
# visualise the mapped shorelines, there are two options:
# if settings['check_detection'] = True, shows the detection to the user for accept/reject
# if settings['save_figure'] = True, saves a figure for each mapped shoreline
if settings['check_detection'] or settings['save_figure']:
date = filenames[i][:19]
if not settings['check_detection']:
plt.ioff() # turning interactive plotting off
skip_image = show_detection(im_ms, cloud_mask, im_labels, shoreline,
image_epsg, georef, settings, date, satname)
# if the user decides to skip the image, continue and do not save the mapped shoreline
if skip_image:
continue
# append to output variables
output_timestamp.append(metadata[satname]['dates'][i])
output_shoreline.append(shoreline)
output_filename.append(filenames[i])
output_cloudcover.append(cloud_cover)
output_geoaccuracy.append(metadata[satname]['acc_georef'][i])
output_idxkeep.append(i)
output_t_mndwi.append(t_mndwi)
# create dictionnary of output
output[satname] = {
'dates': output_timestamp,
'shorelines': output_shoreline,
'filename': output_filename,
'cloud_cover': output_cloudcover,
'geoaccuracy': output_geoaccuracy,
'idx': output_idxkeep,
'MNDWI_threshold': output_t_mndwi,
}
print('')
# close figure window if still open
if plt.get_fignums():
plt.close()
# change the format to have one list sorted by date with all the shorelines (easier to use)
output = SDS_tools.merge_output(output)
# save outputput structure as output.pkl
filepath = os.path.join(filepath_data, sitename)
with open(os.path.join(filepath, sitename + '_output.pkl'), 'wb') as f:
pickle.dump(output, f)
return output
def evaluate_classifier(classifier, metadata, settings):
"""
Interactively visualise the new classifier.
KV WRL 2018
Arguments:
-----------
classifier: joblib object
Multilayer Perceptron to be used for image classification
metadata: dict
contains all the information about the satellite images that were downloaded
settings: dict
contains the following fields:
cloud_thresh: float
value between 0 and 1 indicating the maximum cloud fraction in the image that is accepted
sitename: string
name of the site (also name of the folder where the images are stored)
cloud_mask_issue: boolean
True if there is an issue with the cloud mask and sand pixels are being masked on the images
labels: dict
the label name (key) and label number (value) for each class
filepath_train: str
directory in which to save the labelled data
Returns:
-----------
"""
# create folder
fp = os.path.join(os.getcwd(), 'evaluation')
if not os.path.exists(fp):
os.makedirs(fp)
# initialize figure
fig, ax = plt.subplots(1,
2,
figsize=[17, 10],
sharex=True,
sharey=True,
constrained_layout=True)
mng = plt.get_current_fig_manager()
mng.window.showMaximized()
# create colormap for labels
cmap = cm.get_cmap('tab20c')
colorpalette = cmap(np.arange(0, 13, 1))
colours = np.zeros((3, 4))
colours[0, :] = colorpalette[5]
colours[1, :] = np.array([204 / 255, 1, 1, 1])
colours[2, :] = np.array([0, 91 / 255, 1, 1])
# loop through satellites
for satname in metadata.keys():
filepath = SDS_tools.get_filepath(settings['inputs'], satname)
filenames = metadata[satname]['filenames']
# load classifiers and
if satname in ['L5', 'L7', 'L8']:
pixel_size = 15
elif satname == 'S2':
pixel_size = 10
# convert settings['min_beach_area'] and settings['buffer_size'] from metres to pixels
buffer_size_pixels = np.ceil(settings['buffer_size'] / pixel_size)
min_beach_area_pixels = np.ceil(settings['min_beach_area'] /
pixel_size**2)
# loop through images
for i in range(len(filenames)):
# image filename
fn = SDS_tools.get_filenames(filenames[i], filepath, satname)
# read and preprocess image
im_ms, georef, cloud_mask, im_extra, im_QA, im_nodata = SDS_preprocess.preprocess_single(
fn, satname, settings['cloud_mask_issue'])
image_epsg = metadata[satname]['epsg'][i]
# calculate cloud cover
cloud_cover = np.divide(
sum(sum(cloud_mask.astype(int))),
(cloud_mask.shape[0] * cloud_mask.shape[1]))
# skip image if cloud cover is above threshold
if cloud_cover > settings['cloud_thresh']:
continue
# calculate a buffer around the reference shoreline (if any has been digitised)
im_ref_buffer = SDS_shoreline.create_shoreline_buffer(
cloud_mask.shape, georef, image_epsg, pixel_size, settings)
# classify image in 4 classes (sand, whitewater, water, other) with NN classifier
im_classif, im_labels = SDS_shoreline.classify_image_NN(
im_ms, im_extra, cloud_mask, min_beach_area_pixels, classifier)
# there are two options to map the contours:
# if there are pixels in the 'sand' class --> use find_wl_contours2 (enhanced)
# otherwise use find_wl_contours2 (traditional)
try: # use try/except structure for long runs
if sum(sum(im_labels[:, :, 0])) < 10:
# compute MNDWI image (SWIR-G)
im_mndwi = SDS_tools.nd_index(im_ms[:, :, 4],
im_ms[:, :, 1], cloud_mask)
# find water contours on MNDWI grayscale image
contours_mwi = SDS_shoreline.find_wl_contours1(
im_mndwi, cloud_mask, im_ref_buffer)
else:
# use classification to refine threshold and extract the sand/water interface
contours_wi, contours_mwi = SDS_shoreline.find_wl_contours2(
im_ms, im_labels, cloud_mask, buffer_size_pixels,
im_ref_buffer)
except:
print('Could not map shoreline for this image: ' +
filenames[i])
continue
# process the water contours into a shoreline
shoreline = SDS_shoreline.process_shoreline(
contours_mwi, cloud_mask, georef, image_epsg, settings)
try:
sl_pix = SDS_tools.convert_world2pix(
SDS_tools.convert_epsg(shoreline, settings['output_epsg'],
image_epsg)[:, [0, 1]], georef)
except:
# if try fails, just add nan into the shoreline vector so the next parts can still run
sl_pix = np.array([[np.nan, np.nan], [np.nan, np.nan]])
# make a plot
im_RGB = SDS_preprocess.rescale_image_intensity(
im_ms[:, :, [2, 1, 0]], cloud_mask, 99.9)
# create classified image
im_class = np.copy(im_RGB)
for k in range(0, im_labels.shape[2]):
im_class[im_labels[:, :, k], 0] = colours[k, 0]
im_class[im_labels[:, :, k], 1] = colours[k, 1]
im_class[im_labels[:, :, k], 2] = colours[k, 2]
# show images
ax[0].imshow(im_RGB)
ax[1].imshow(im_RGB)
ax[1].imshow(im_class, alpha=0.5)
ax[0].axis('off')
ax[1].axis('off')
filename = filenames[i][:filenames[i].find('.')][:-4]
ax[0].set_title(filename)
ax[0].plot(sl_pix[:, 0], sl_pix[:, 1], 'k.', markersize=3)
ax[1].plot(sl_pix[:, 0], sl_pix[:, 1], 'k.', markersize=3)
# save figure
fig.savefig(os.path.join(
fp, settings['inputs']['sitename'] + filename[:19] + '.jpg'),
dpi=150)
# clear axes
for cax in fig.axes:
cax.clear()
# close the figure at the end
plt.close()