geetools_VH/read_images2.py

# -*- coding: utf-8 -*-

#==========================================================#
# Extract shorelines from Landsat images
#==========================================================#

# Initial settings
import os
import numpy as np
import matplotlib.pyplot as plt
import ee
import pdb

# other modules
from osgeo import gdal, ogr, osr
import pickle
import matplotlib.cm as cm
from pylab import ginput

# image processing modules
import skimage.filters as filters 
import skimage.exposure as exposure
import skimage.transform as transform
import sklearn.decomposition as decomposition
import skimage.measure as measure
import skimage.morphology as morphology

# machine learning modules
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPClassifier
from sklearn.preprocessing import StandardScaler, Normalizer 
from sklearn.externals import joblib

# import own modules
import functions.utils as utils
import functions.sds as sds

# some settings
np.seterr(all='ignore') # raise/ignore divisions by 0 and nans
plt.rcParams['axes.grid'] = True
plt.rcParams['figure.max_open_warning'] = 100
ee.Initialize()

# parameters
cloud_thresh = 0.3      # threshold for cloud cover
plot_bool = False      # if you want the plots
min_contour_points = 100# minimum number of points contained in each water line
output_epsg = 28356     # GDA94 / MGA Zone 56
buffer_size = 7        # radius (in pixels) of disk for buffer (pixel classification)
min_beach_size = 50     # number of pixels in a beach (pixel classification)

# load metadata (timestamps and epsg code) for the collection
satname = 'L8'
sitename = 'NARRA'
#sitename = 'OLDBAR'

# Load metadata
filepath = os.path.join(os.getcwd(), 'data', satname, sitename)
with open(os.path.join(filepath, sitename + '_timestamps' + '.pkl'), 'rb') as f:
    timestamps = pickle.load(f)
with open(os.path.join(filepath, sitename + '_accuracy_georef' + '.pkl'), 'rb') as f:
    acc_georef = pickle.load(f) 
with open(os.path.join(filepath, sitename + '_epsgcode' + '.pkl'), 'rb') as f:
    input_epsg = pickle.load(f)
with open(os.path.join(filepath, sitename + '_refpoints' + '.pkl'), 'rb') as f:
    refpoints = pickle.load(f)
# sort timestamps and georef accuracy (dowloaded images are sorted by date in directory)
timestamps_sorted = sorted(timestamps)
idx_sorted = sorted(range(len(timestamps)), key=timestamps.__getitem__)
acc_georef_sorted = [acc_georef[j] for j in idx_sorted]

# path to images
file_path_pan = os.path.join(os.getcwd(), 'data', satname, sitename, 'pan')
file_path_ms = os.path.join(os.getcwd(), 'data', satname, sitename, 'ms')
file_names_pan = os.listdir(file_path_pan)
file_names_ms = os.listdir(file_path_ms)
N = len(file_names_pan)

# initialise some variables
cloud_cover_ts = []
date_acquired_ts = []
acc_georef_ts = []
idx_skipped = []
idx_nocloud = []
t = []
shorelines = []
idx_keep = []
#%%
for i in range(N):
    
    # read pan image
    fn_pan = os.path.join(file_path_pan, file_names_pan[i])
    data = gdal.Open(fn_pan, gdal.GA_ReadOnly)
    georef = np.array(data.GetGeoTransform())
    bands = [data.GetRasterBand(i + 1).ReadAsArray() for i in range(data.RasterCount)]
    im_pan = np.stack(bands, 2)[:,:,0]
    nrows = im_pan.shape[0]
    ncols = im_pan.shape[1]
    
    # read ms image
    fn_ms = os.path.join(file_path_ms, file_names_ms[i])
    data = gdal.Open(fn_ms, gdal.GA_ReadOnly)
    bands = [data.GetRasterBand(i + 1).ReadAsArray() for i in range(data.RasterCount)]
    im_ms = np.stack(bands, 2)
    
    # cloud mask
    im_qa = im_ms[:,:,5]
    cloud_mask = sds.create_cloud_mask(im_qa, satname, plot_bool)
    cloud_mask = transform.resize(cloud_mask, (im_pan.shape[0], im_pan.shape[1]),
                                order=0, preserve_range=True, 
                                mode='constant').astype('bool_')    
    # resize the image using bilinear interpolation (order 1)
    im_ms = transform.resize(im_ms,(im_pan.shape[0], im_pan.shape[1]),
                             order=1, preserve_range=True, mode='constant')
    
    # check if -inf or nan values and add to cloud mask
    im_inf = np.isin(im_ms[:,:,0], -np.inf)
    im_nan = np.isnan(im_ms[:,:,0])
    cloud_mask = np.logical_or(np.logical_or(cloud_mask, im_inf), im_nan)
    
    # calculate cloud cover and skip image if too high
    cloud_cover = sum(sum(cloud_mask.astype(int)))/(cloud_mask.shape[0]*cloud_mask.shape[1])
    if cloud_cover > cloud_thresh:
        print('skip ' + str(i) + ' - cloudy (' + str(cloud_cover) + ')')
        idx_skipped.append(i)
        continue
    idx_nocloud.append(i)
    
    # check if image for that date already exists and choose the best in terms of cloud cover and georeferencing
    if file_names_pan[i][len(satname)+1+len(sitename)+1:len(satname)+1+len(sitename)+1+10] in date_acquired_ts:
        
        # find the index of the image that is repeated
        idx_samedate = utils.find_indices(date_acquired_ts, lambda e : e == file_names_pan[i][9:19])
        idx_samedate = idx_samedate[0]
        print('cloud cover ' + str(cloud_cover) + ' - ' + str(cloud_cover_ts[idx_samedate]))
        print('acc georef ' + str(acc_georef_sorted[i]) + ' - ' + str(acc_georef_ts[idx_samedate]))
        
        # keep image with less cloud cover or best georeferencing accuracy
        if cloud_cover < cloud_cover_ts[idx_samedate] - 0.01: 
            skip = False
        elif acc_georef_sorted[i] < acc_georef_ts[idx_samedate]:
            skip = False
        else:
            skip = True
            
        if skip:
            print('skip ' + str(i) + ' - repeated')
            idx_skipped.append(i)
            continue
        else:
#            del shorelines[idx_samedate]
            del t[idx_samedate]
            del cloud_cover_ts[idx_samedate]
            del date_acquired_ts[idx_samedate]
            del acc_georef_ts[idx_samedate]
            print('keep ' + str(i) + ' - deleted ' + str(idx_samedate))
            
    # pansharpen rgb image
    im_ms_ps = sds.pansharpen(im_ms[:,:,[0,1,2]], im_pan, cloud_mask, plot_bool)
    # rescale pansharpened RGB for visualisation
    im_display = sds.rescale_image_intensity(im_ms_ps[:,:,[2,1,0]], cloud_mask, 100, False)
    # add down-sized bands for NIR and SWIR (since pansharpening is not possible)
    im_ms_ps = np.append(im_ms_ps, im_ms[:,:,[3,4]], axis=2) 
    
    # classify image in 4 classes (sand, whitewater, water, other) with NN classifier
    im_classif, im_labels = sds.classify_image_NN(im_ms_ps, im_pan, cloud_mask, min_beach_size, plot_bool)
    idx_keep.append(i)
    if sum(sum(im_labels[:,:,0])) == 0 :
        print('skip ' + str(i) + ' - no sand')
        idx_skipped.append(i)
        continue
    
    # extract shorelines (new method)
    contours_wi, contours_mwi = sds.find_wl_contours2(im_ms_ps, im_labels, cloud_mask, buffer_size, True)
    
    t.append(timestamps_sorted[i])
    cloud_cover_ts.append(cloud_cover)
    acc_georef_ts.append(acc_georef_sorted[i])
    date_acquired_ts.append(file_names_pan[i][9:19])