def attribute_segments(listInputs):
dataStack = listInputs[0]# data with values
habFile = listInputs[1] # data with habitat codes
clumpsFile = listInputs[2] # segments
# Populate with stats, so it can be read for the RAT
rastergis.populateStats(dataStack)
rastergis.populateStats(clumpsFile)
rastergis.populateStats(habFile)
ratutils.populateImageStats(dataStack, clumpsFile, calcMean=True)
# Convert training data to RAT!!!
codeStats = [] #list()
codeStats.append(rastergis.BandAttStats(band=1, minField='Class'))
rastergis.populateRATWithStats(habFile, habFile, codeStats)
# Attribute segments with class: yes, so I can compare later !!
rastergis.strClassMajority(clumpsFile, habFile, 'Class', 'Class', False)
##############################################################################################
# Shepherd segmentation - this output will be used in second script to run classifier
##############################################################################################
print('Performing the segmentation...')
outputClumps=inputImage.replace('.tif','_clumps2.kea')
outputMeanImg=inputImage.replace('.tif','_clumps2_mean.kea')
segutils.runShepherdSegmentation(inputImage, outputClumps, outputMeanImg, minPxls=100)
bandList=['VV','VH','VVdivVH']
rsgislib.imageutils.setBandNames(outputMeanImg, bandList)
rastergis.populateStats(outputClumps, True, True, True, 1)
rastergis.populateStats(outputMeanImg, True, True, True, 1)
clumps=outputClumps # rename clumps image
ratutils.populateImageStats(inputImage, clumps, calcMin=True,calcMax=True,calcMean=True, calcStDev=True) # add radar stats
##############################################################################################
# add global urban footprint stats
gufSnap=guf.split('.')[0]+'_'+inputImage.split('/')[-1].split('_')[4]+'.tif'
inRefImg=clumps # base raster to snap to
gdalFormat = 'GTiff'
rsgislib.imageutils.resampleImage2Match(inRefImg, guf, gufSnap, gdalFormat, interpMethod='nearestneighbour', datatype=None) # perform resampling/snap
bandList=['guf']
rsgislib.imageutils.setBandNames(gufSnap, bandList)
ratutils.populateImageStats(gufSnap, clumps, calcMax=True) # add urban footprint stats
# remove the intermediate snapped guf image
try:
os.remove(gufSnap)
print('Performing the segmentation...')
segutils.runShepherdSegmentation(inputImg,
outputClumps,
outputMeanImg,
minPxls=100)
gdalformat = 'KEA'
# rsgislib.segmentation.generateRegularGrid(inputImg, outputClumps, gdalformat, 1, 1)
rastergis.populateStats(outputClumps, True, True, True, 1)
bandList = ['VV', 'VH', 'VVdivVH']
rsgislib.imageutils.setBandNames(inputImg, bandList)
rsgislib.imageutils.setBandNames(outputMeanImg, bandList)
rastergis.populateStats(outputMeanImg, True, True, True, 1)
# populate RAT with mean stats from S1
clumps = outputClumps # rename clumps image
ratutils.populateImageStats(inputImg, clumps, calcMean=True, calcStDev=True)
# populate clumps with training data
print('Populating clumps with stats...')
classesDict = dict()
classesDict['Water'] = [
1,
'/Users/Andy/Documents/Zambia/RemoteSensing/WB_classification/Supporting_data/global_surface_water/watermask_barotseland_m18dB_20170704.shp'
]
tmpPath = './temp'
classesIntCol = 'ClassInt'
classesNameCol = 'ClassStr'
ratutils.populateClumpsWithClassTraining(clumps, classesDict, tmpPath,
classesIntCol, classesNameCol)
#
outputMeanImg = inputImage.split('.')[0]+'_clust5_clumps2_mean.kea'
segutils.runShepherdSegmentation(inputImage, outputClumps, outputMeanImg, minPxls=100, numClusters=5)
# set output band names
bandList=['VV','VH','VVdivVH']
#rsgislib.imageutils.setBandNames(inputImage, bandList)
rsgislib.imageutils.setBandNames(outputMeanImg, bandList)
# rastergis.populateStats(outputMeanImg, True, True, True, 1)
# populate RAT with mean stats from S1
clumps=outputClumps # rename clumps image
ratutils.populateImageStats(inputImage, clumps, calcMin=True,calcMax=True,calcMean=True, calcStDev=True)
##############################################################################################
# snap the sand exclusion layer and populate to RAT
bandList=['SEL']
rsgislib.imageutils.setBandNames(sand_exclusion, bandList)
sand_exclusion_snap=sand_exclusion.replace('.kea','_snapped.kea')
gdalFormat = 'KEA'
inRefImg=inputImage
rsgislib.imageutils.resampleImage2Match(inRefImg, sand_exclusion, sand_exclusion_snap, gdalFormat, interpMethod='nearestneighbour', datatype=None) # perform resampling/snap
ratutils.populateImageStats(sand_exclusion_snap, clumps, calcMax=True,calcMean=True)
##############################################################################################
for clumps in listFiles:
try:
print('')
print('Processing: ' + clumps)
#clumps=listFiles[0]
outImage = clumps.replace('.kea', '_erf_clumptrain_mode_sel.tif')
print('')
# print('SEL: ' + sel)
# print('clumps: ' + clumps)
print('')
ratutils.populateImageStats(sel,
clumps,
calcMax=True,
calcMean=True,
calcMin=True) # add SEL statistics to RAT
ratutils.populateImageStats(guf, clumps,
calcMax=True) # add SEL statistics to RAT
#ratutils.populateImageStats(waterPerm,clumps,calcMean=True) # add water permanance statistics to RAT
# Open RAT
ratDataset = gdal.Open(clumps, gdal.GA_Update)
data = []
# Read in data from class_cert and sel columns
data.append(rat.readColumn(ratDataset, 'OutClass_mode_cert'))
data.append(rat.readColumn(ratDataset, 'SELMax'))
data.append(rat.readColumn(ratDataset, 'gufMax'))
mode_cert = data[0]
noStretch=True, # Issue when this is false
noStats=True, # Issue when this is false
numClusters=60,
minPxls=25,
distThres=10,
sampling=100,
kmMaxIter=200)
# ------------------------------------------------- #
# Image statistics
print('Calculating image statistics...')
# Spectral stats
rastergis.populateStats(segments_fn)
ratutils.populateImageStats(
stan_rast_fn,
segments_fn,
calcMean=True,
calcMin=True,
calcMax=True,
calcStDev=True) # populates clumps file with stats
# reading in RAT to add to
segment_rat = gdal.Open(
segments_fn, gdal.GA_Update) # Read in segments raster as gdal
segment_ds = segment_rat.GetRasterBand(
1).GetDefaultRAT() # Read in RAT
band = segment_rat.GetRasterBand(
1).ReadAsArray() # read in segment raster band, with seg ids
band_data = np.dstack(band)
segment_ids = np.unique(band) # extract seg ids
# ------------------------------------ #
# create list of object stats, where each row is an object ro1[1] = [1,2,3,4,5]
##############################################################################################
# add global urban footprint stats
gufSnap = guf.split('.')[0] + '_' + inputImage.split('_')[4] + '.tif'
inRefImg = clumps # base raster to snap to
gdalFormat = 'GTiff'
rsgislib.imageutils.resampleImage2Match(
inRefImg,
guf,
gufSnap,
gdalFormat,
interpMethod='nearestneighbour',
datatype=None) # perform resampling/snap
bandList = ['guf']
rsgislib.imageutils.setBandNames(gufSnap, bandList)
ratutils.populateImageStats(gufSnap, clumps,
calcMax=True) # add urban footprint stats
# remove the intermediate snapped guf image
try:
os.remove(gufSnap)
except Exception:
pass
##############################################################################################
# Extracting training data masks
##############################################################################################
waterSnap = globalWater.split('.')[0] + '_' + inputImage.split(
'_')[4] + '_clump.tif'
inRefImg = inputImage # base raster to snap to
gdalFormat = 'GTiff'
