def classification(data):
# Add channel
pcimod(file=inputfile, pciop='add', pcival=[0, 0, 1, 0, 0, 0])
# Define input parameters
classesNumber = [8] # define number of classes
iterations = [10] # define number iterations
moveThresh = [0.01] # define move threshhold
print "Running unsupervized k-means classification..."
print "Creating " + str(classesNumber) + " classes, applying " + str(
iterations) + " iterations at a move-threshhold of " + str(
moveThresh)
# Run algorithm and create classification report
try:
Report.clear()
enableDefaultReport(report)
kclus(file=inputfile,
dbic=inputChans,
dboc=[chansCount + 1],
numclus=classesNumber,
maxiter=iterations,
movethrs=moveThresh)
finally:
enableDefaultReport('term') # this will close the report file
flag1 = time.time()
print "Classification complete! Time elapsed: " + str(
flag1 - start) + " seconds"
print ""
def SIEVE(data):
# Add channel
pcimod(file=inputfile, pciop='add', pcival=[0, 0, 1, 0, 0, 0])
print "Applying sieve..."
# Run algorithm
sieve(file=inputfile,
dbic=[chansCount + 2],
dboc=[chansCount + 3],
sthresh=[32])
flag3 = time.time()
print "Sieve complete! Time elapsed: " + str(flag3 -
start) + " seconds"
print ""
def FMO(data):
# Add channel
pcimod(file=inputfile, pciop='add', pcival=[0, 0, 1, 0, 0, 0])
print "Running Mode Filter..."
filter = [5, 5]
# Run algorithm
fmo(file=inputfile,
dbic=[chansCount + 1],
dboc=[chansCount + 2],
thinline="OFF",
flsz=filter)
flag2 = time.time()
print "Filtering complete! Time elapsed: " + str(flag2 -
start) + " seconds"
print ""
def getChannelNumber(channelName):
global dataset, auxiliaryData
# Scan for channel name
for i in range(1, dataset.chan_count + 1):
if (auxiliaryData.get_chan_description(i).startswith(channelName)):
return i
# Scan for empty channel
for i in range(1, dataset.chan_count + 1):
if (auxiliaryData.get_chan_description(i) == 'Contents Not Specified'):
qprintl('Use empty channel #{} for {}'.format(i, channelName))
setChannelDescription(i, channelName)
return i
qprint('Creating a new channel for {}...'.format(channelName))
pcimod(file=dataset.name, pciop='ADD', pcival=[1, 0, 0, 0])
dataset = datasource.open_dataset(dataset.name, datasource.eAM_WRITE)
auxiliaryData = dataset.aux_data
qprintl('OK')
return getChannelNumber(channelName)
def add_32_channel(self, in_file):
"""
Add 8 bit channel to file
Note:
PCI's developers are going to try to add a 'last segment created' (lasc) parameter for
this function in the next release, thereby enabling cleaner and more reliable automation.
Parameters:
in_file -- Input file
Return value:
Newly created channel number, error statement otherwise.
Limits and constraints:
"""
from pci.api import datasource as ds
from pci.pcimod import pcimod
from pci.exceptions import PCIException
## from pci.his import *
from pci.nspio import Report, enableDefaultReport
from osgeo import gdal, ogr, osr
## from gdalconst import *
import numpy
try:
logging.info(' Executing: EGSUtility.add_32_channel')
file = in_file
pciop = 'ADD'
pcival = [0, 0, 0, 1]
list_before = self.create_chan_list(
in_file) # Create the list of channels before running pcimod
pcimod(file, pciop, pcival)
list_after = self.create_chan_list(
in_file) # Create the list of channels after running pcimod
new_chans = self.compare_list(
list_before, list_after
) # Compare the list from before and after running pcimod
return new_chans
except PCIException, e:
self.error('add_32_channel(): {:s}'.format(e))
exit(3)
channels = []
try:
channels = [int(n) for n in sys.argv[4].split(",")]
except ValueError as e:
print "Conversion error [STRING >> INT]", e
exit(2)
out = os.path.splitext(os.path.basename(sys.argv[1]))[0] + ".pix"
out = out.replace("-M2AS-", "-PSH2-")
out = sys.argv[3] + os.path.sep + out
if os.path.exists(out):
try:
os.remove(out)
except OSError as e:
print "Unable to remove %s: %s" % (out, e)
exit(-1)
pansharp2(sys.argv[1], channels, channels, sys.argv[2], [1], out, channels,
u"YES", u"FILE,0", u"OFF", u"PIX", u"TILED256")
l = len(channels)
pcimod(out, u"ADD", [0, 0, 3, 0, 0, 0])
ihs(out, [1, 2, 3], list(range(l + 1, l + 4)), [], u"CYLINDER")
pyramid(out, [], u"YES", [-2], u"AVERAGE")
def classification(self, file, alg):
if (alg == 'kmeans'):
print("Your selection is K-means Classification")
else:
print("Your selection is Iso-Cluster Classification")
report = os.getcwd() + "\\Data\\Result\\Report.txt"
if os.path.isfile(report):
print("Deleting old Report")
os.remove(report)
with datasource.open_dataset(file) as dataset:
cc = dataset.chan_count
print("Available Channels: ")
print(cc)
if (alg == 'kmeans'):
file = file
dbic = list(range(1, cc + 1, 1)) # input channels
dboc = [cc + 1] # output channel
print(dboc)
mask = [] # process entire image
numclus = [5] # requested number of clusters
seedfile = '' # automatically generate seeds
maxiter = [20] # no more than 20 iterations
movethrs = [0.01]
print("The file is: " + root.filename)
## enableDefaultReport(prev_report)
pcimod(file=file, pciop='add', pcival=[1, 0, 0, 0, 0, 0])
Report.clear()
enableDefaultReport(report)
print("Applying K-Means Classification")
kcluster = kclus(file, dbic, dboc, mask, numclus, seedfile,
maxiter, movethrs)
print("K-Means Classification is successful")
else:
file = file # input file
dbic = list(range(1, cc + 1, 1)) # input channels
dboc = [cc + 1] # output channel
print(dboc)
mask = [] # process entire image
numclus = [5] # requested number of clusters
maxclus = [7] # at most 20 clusters
minclus = [5] # at least 5 clusters
seedfile = '' # automatically generate seeds
maxiter = [5] # no more than 20 iterations
movethrs = [0.01]
siggen = "NO" # no signature generation
samprm = [5]
stdv = [10.0]
lump = [1.0]
maxpair = [5] # no more than 5 cluster center pairs
# clumped in one iteration
backval = [] # no background value
nsam = [] # default number of samples
print("The file is: " + root.filename)
## enableDefaultReport(prev_report)
pcimod(file=file, pciop='add', pcival=[1, 0, 0, 0, 0, 0])
Report.clear()
enableDefaultReport(report)
print("Applying Iso-cluster Classification")
isoclus( file, dbic, dboc, mask, numclus, maxclus, minclus, seedfile, maxiter,\
movethrs, siggen, samprm, stdv, lump, maxpair, backval, nsam )
print("Iso-Cluster Classification is successful")
pcimod(file=file, pciop='add', pcival=[1])
## root.status.set("Running fmo")
print("Applying MOD filter")
kfmo = fmo(file=file, dbic=[cc + 1], dboc=[cc + 2])
print("MOD filter is successfully applied")
pcimod(file=file, pciop='add', pcival=[1])
## root.status.set("Running sieve")
print("Applying SIEVE filter")
ksieve = sieve(file=file, dbic=[cc + 1], dboc=[cc + 3], sthresh=[32])
print("SIEVE filter is successfully applied")
## Split and insert directory name
split_file = file.split("/")
split_file.insert(-1, "Result")
join_result = "\\".join(split_file)
## Split by .
dot_result = join_result.split(".")
## print(dot_result)
## print("dot result")
## join .shp at last
shp_result = dot_result[0] + ".shp"
current_file_path, ext = os.path.splitext(str(file))
current_file = current_file_path.split("/")[-1]
## print(current_file)
## print("current file")
## Delete previously generated shapefiles
prev_files = glob.glob(os.getcwd() + "\\Data\\Result\\" + "*")
## print(prev_files)
## print("previous files")
for prev_file in prev_files:
prev_file_name, format = os.path.splitext(
str(os.path.basename(prev_file)))
## print(prev_file_name)
## print(" prev file names")
if (current_file in prev_file_name):
print("DELETING: " + str(prev_file))
os.remove(prev_file)
print("Successfully DELETED: " + str(prev_file))
## if(os.path.exists("../Data/Result/"+dot_result[0])):
## print("inside if ......")
## os.remove(shp_result)
## print("shp is deleted...")
print("Exporting to shapefile")
ras2poly(fili=file,
dbic=[cc + 3],
filo=shp_result,
smoothv="Yes",
ftype="SHP",
foptions="")
print("Shapefile is successfully created")
def icemapr(infile,
infilec,
inmask,
inmasks,
inpct,
outfile,
logfile=None,
logdetails=2):
"""
IceMAP-R algorithm for river ice using SAR images with HH polarization
Parameters:
INFILE : Name of the file for the ortorectified HH radar image
INFILEC : Channel number in INFILE for the HH radar image to use
INMASK : Name of the file for the georeferenced vector of the river polygon
INMASKS : Segment number in INMASK for the vector to use
INPCT : Name of the file for the legend or predefined type (freeze, thaw)
OUTFILE : Name of the output file
LOGFILE : Name of the log file
LOGDETAILS : Threshold of log details. From 1 to 5. 1=high detail log, 5=low detail log
Details:
IceMAP-R uses PCIDSK format for intermediate results because it is the more convenient format, and often the only
one that we can use with Geomatica functions. PCIDSK is a data structure for holding digital images and related
data, such as LUTs, vectors, bitmaps, and other data types.
Segments are the parts of a PCIDSK database which hold data related to the imagery in the database. A database
can store up to 1024 segments, provided you have enough disk space. Twelve kinds of information are stored as
segments. Vectors is one type. To see the segment number of a specific information in a PCIDSK, you need to go
in the Files tab in Geomatica FOCUS and explore the desired file structure. For the Shapefile format, all the
data are considered to be in segment number 1.
Pseudocolor Tables are another type of segment (PCT). Pseudocolor segments hold numerical tables which map
image DN values to a specific color. Colors are defined by an intensity value (between 0 and 255) for each of
the red, green, and blue component. For the INPCT parameter, a custom pseudocolor table can be supplied in text
format. For a template, look in the createPCT function below or in Geomatica Help. That function creates a text
file for two predefined pseudocolor tables used in IceMAP-R. A PCT segment contains an array of 256 colors and
assigns color values to 8-bit images. A PCT always contains exactly 256 entries. In the text file, entries can
be grouped using range.
Constraints:
Need to be executed with Python 2.7 in 64 bits and Geomatica Prime 2015 with service pack 1 or numpy 1.8.2+
To get more information about PCI modules, see python algorithm reference
http://www.pcigeomatics.com/geomatica-help/index.html?page=concepts%2Falgoreference_c%2Fpace2n100.html
"""
if setupLogger(logfile, logdetails * 10):
#Log opening message
logger.info("- Version python [{0}]".format(sys.version))
logger.info(
"- Function call [{0}, {1}, {2}, {3}, {4}, {5}, {6}, {7}]".format(
infile, infilec, inmask, inmasks, inpct, outfile, logfile,
logdetails))
logging.info("Checking validity of inputs parameters")
# Check input files
for f, k in zip([infile, inmask], ['Input image file', 'Input mask']):
if not os.path.exists(f):
logger.error("{0} doesn't exists! Looked for {1}".format(k, f))
return False
if os.path.splitext(inmask)[1] == '.shp':
if inmasks != 1:
logger.warning(
"The segment number for a shapefile is always 1. Input value changed for the process!"
)
inmasks = 1
if inpct.lower() in ['freeze', 'thaw']:
pct2use = createPCT(inpct)
elif os.path.splitext(inpct)[1] == '.txt':
if not os.path.exists(inpct):
logger.error(
"PCT file doesn't exists! Looked for {0}".format(inpct))
return False
pct2use = inpct
else:
logger.error('Invalid legend file format! Need to be a text file.')
return 1
# Check output file
if os.path.exists(outfile):
#File already exists
logger.error(
'Output file already exists! The file must be deleted before running this process.'
)
return False
filename, file_extension = os.path.splitext(outfile)
try:
logging.info(
"Creation of the temporary file to copy the input image and intermediate results"
)
# Temporary file with the date and time
tempDir = tempfile.gettempdir()
tmpfile = os.path.join(
tempDir, "icemap_tmpfile_{0}.pix".format(
datetime.now().strftime("%y%m%d_%H%M%S")))
logger.info(
'*Temporary file name for the process : {0}'.format(tmpfile))
logger.info(
'*It will be deleted if the icemap is produced succeesfully')
# Getting information about the HH polarized RS2 image (pixel height and width)
dataset = ds.open_dataset(infile)
height = dataset.height
width = dataset.width
logging.info(" Creation of the database")
# Creation of image database file to copy the input image and results
ifile = tmpfile # File name
tex1 = "Temporary file for Icemap results" # Descriptive text
tex2 = '' # Text
dbsz = [width, height] # X pixels by Y lines
pxsz = [] # Meter resolution [x,y]
dbnc = [6, 0, 0, 0] # Six 8-bit channels
dblayout = "BAND" # Use band interleaving
cim(ifile, tex1, tex2, dbsz, pxsz, dbnc, dblayout)
# A georeferencing segment is automatically created as the first segment of the new file.
segment = 1
logging.info(" Copy of the projection")
# Projection copy from the current pix into temporary file
src_crs = dataset.crs
src_gc = dataset.geocoding
writer = ds.BasicWriter(tmpfile)
writer.crs = src_crs
writer.geocoding = src_gc
logging.info(" Adding channels for intermediate results")
# Add new image channels to existing file
channels = [0, 0, 0, 6] # Add 6x 32bit real channels
pcimod(ifile, "ADD", channels)
logging.info(" Copy of the original image")
# Database to database image transfert
chan_sar = [7]
fili = infile # Input file name
filo = tmpfile # Output file name
dbic = [infilec] # Input raster channel
dboc = chan_sar # Output raster channel
dbiw = [] # Raster input window - Use full image
dbow = [] # Raster output window - Use full image
iii(fili, filo, dbic, dboc, dbiw, dbow)
logging.info(
"Conversion of river mask in bitmap segment inside temporary file")
# Conversion of river mask in bitmap segment
fili = inmask # Input polygon file
dbvs = [inmasks] # Polygon layer
filo = tmpfile # Output file name
dbsd = 'River mask' # Segment descriptor
pixres = [] # Pixels resolution equal to output image
ftype = '' # Output file extension
foptions = '' # Output format type
poly2bit(fili, dbvs, filo, dbsd, pixres, ftype, foptions)
segment += 1
riverMask = segment
logging.info(
"Cropping bitmap for the area that is covered by input image")
# Bitmap crop of the area that is covered in both images
source = """if (%{0[0]}=0) then
%%{1}=0;
endif;""".format(chan_sar, riverMask)
undefval = []
model(ifile, source, undefval)
logging.info("Computing texture analysis")
# Texture analysis
chan_tex = [8, 9, 10]
dbic = chan_sar # Input raster image channel
texture = [2, 4, 7] # Select required texture
dboc = chan_tex # Output channels chan_tex[1],chan_tex[2],chan_tex[3]
flsz = [7, 7] # Filter Size in pixels
greylev = [256] # Number of gray levels
spatial = [1, 1] # Spatial relationship
tex(ifile, dbic, texture, dboc, flsz, greylev, spatial)
logging.info(
"Performing Kuan filtering to remove speckle on the original image data"
)
# Performs Kuan filtering to remove speckle on image data
chan_fkuan = [11]
dbic = chan_sar # Channel to be filtered
dboc = chan_fkuan # Filtered results
flsz = [7, 7] # 7x7 filter size
mask = [] # Filter entire image, area mask
nlook = [1.0] # Number of looks
imagefmt = 'AMP' # Amplitude image format
fkuan(ifile, dbic, dboc, flsz, mask, nlook, imagefmt)
# Modify channel descriptior
desc = 'FKUAN result' # New channel description
dboc = chan_fkuan # Output channel
mcd(ifile, desc, dboc)
logging.info("Performing median filtering")
# Performs median filtering to further smooth image data, while preserving sharp edges
chan_fme = [12]
dbic = chan_fkuan # input channel
dboc = chan_fme # Output channel
flsz = [3, 3] # 3x3 filter
mask = [riverMask] # Bitmap mask segment
bgrange = [] # Background values range
failvalu = [] # Failure value
bgzero = '' # Set background to 0 - Default, YES
fme(ifile, dbic, dboc, flsz, mask, bgrange, failvalu, bgzero)
# Modify channel descriptior
desc = 'FME result' # New channel description
dboc = chan_fme # Output channel
mcd(ifile, desc, dboc)
logging.info(
"Performing unsupervised clustering using the Fuzzy K-means method"
)
# FUZCLUS - Performs unsupervised clustering using the Fuzzy K-means method
chan_fuz1 = [1]
dbic = [chan_tex[1]] # Input channel
dboc = chan_fuz1 # Output channel
mask = [riverMask] # Area mask
numclus = [7] # Requested number of clusters
seedfile = '' # Automatically generate seeds
maxiter = [20] # No more than 20 iterations
movethrs = [0.01] # Movement threshold
siggen = '' # Do not generate signatures
backval = [] # No background value to be ignored
nsam = [] # Number of pixel values to sample - Use default 262144
fuzclus(ifile, dbic, dboc, mask, numclus, seedfile, maxiter, movethrs,
siggen, backval, nsam)
logging.info("Clearing regions smaller than 12 pixels")
# Reads an image channel and merges image value polygons smaller than
# a user-specified threshold with the largest neighboring polygon
chan_sieve = [2]
dbic = chan_fuz1 # Input raster channel
dboc = chan_sieve # Output raster channel
sthresh = [12] # Polygon size threshold
keepvalu = [0] # Value excluded from filtering
connect = [4] # Connectedness of lines
sieve(ifile, dbic, dboc, sthresh, keepvalu, connect)
logging.info("Extracting class 1 for a new classification")
# Extracting class 1
dbic = chan_sieve # Input raster channel
dbob = [] # Create new bitmap
tval = [1, 1] # Threshold range (min,max)
comp = 'OFF' # Complement mode
dbsn = 'THR_1' # Output segment name
dbsd = 'MASK_CLASS_1' # Output segment description
thr(ifile, dbic, dbob, tval, comp, dbsn, dbsd)
segment += 1
class1Mask = segment
logging.info("Reclassification of class 1")
# Reclassification of class 1
chan_fuz2 = [3]
dbic = chan_tex # Input channels
dboc = chan_fuz2 # Output channel
mask = [class1Mask] # Area mask
numclus = [20] # Requested number of clusters
seedfile = "" # Automatically generate seeds
maxiter = [20] # No more than 20 iterations
movethrs = [0.01] # Movement threshold
siggen = "" # Do not generate signatures
backval = [] # No background value to be ignored
nsam = [] # Number of pixel values to sample - Use default 262144
fuzclus(ifile, dbic, dboc, mask, numclus, seedfile, maxiter, movethrs,
siggen, backval, nsam)
logging.info("Extracting class 7 for a new classification")
# Extracting class 7
dbic = chan_sieve # Input raster channel
dbob = [] # Create new bitmap
tval = [7, 7] # Threshold range (min,max)
comp = 'OFF' # Complement mode
dbsn = 'THR_7' # Output segment name
dbsd = 'MASK_CLASS_7' # Output segment description
thr(ifile, dbic, dbob, tval, comp, dbsn, dbsd)
segment += 1
class7Mask = segment
logging.info("Reclassification of class 7")
# Reclassification of class 7
chan_fuzclus3 = [4]
dbic = chan_fme # input channel
dboc = chan_fuzclus3 # output channel
mask = [class7Mask] # mask area
numclus = [8] # requested number of clusters
seedfile = "" # automatically generate seeds
maxiter = [20] # no more than 20 iterations
movethrs = [0.01] # movement threshold
siggen = "" # do not generate signatures
backval = [] # no background value to be ignored
nsam = [] # Number of pixel values to sample - Use default 262144
fuzclus(ifile, dbic, dboc, mask, numclus, seedfile, maxiter, movethrs,
siggen, backval, nsam)
logging.info(
"Final classification - fusion of the three previous classification"
)
# Final classification
chan_mosaic3 = [5]
source = """if (%{0[0]}>1) and (%{0[0]}<7) then
%{1[0]} = %{0[0]}+1;
elseif (%{0[0]} = 1) then
if (%{2[0]}<9) and (%{2[0]}>0) then
%{1[0]} = 1;
elseif (%{2[0]}>=9) then
%{1[0]} = 2;
endif;
elseif (%{0[0]} = 7) then
if (%{3[0]}>=5) then
%{1[0]} = 9;
elseif (%{3[0]}<5) and (%{3[0]}>0) then
%{1[0]} = 8;
endif;
endif;""".format(chan_sieve, chan_mosaic3, chan_fuz2, chan_fuzclus3)
undefval = [] #Value for undefined operations
model(ifile, source, undefval)
mcd(tmpfile, 'Model', chan_mosaic3)
logging.info("Clearing regions smaller than 12 pixels")
# Reads an image channel and merges image value polygons smaller than
# a user-specified threshold with the largest neighboring polygon
chan_sieve2 = [6]
dbic = chan_mosaic3 # Input raster channel
dboc = chan_sieve2 # Output raster channel
sthresh = [12] # Polygon size threshold
keepvalu = [0] # Value excluded from filtering
connect = [4] # Connectedness of lines
sieve(ifile, dbic, dboc, sthresh, keepvalu, connect)
logging.info("Importation of the pseudocolor table data")
# reads a pseudocolor table from a textfile and transfers the data into a database file
ifile = tmpfile # Output file name
dbpct = [] # Output PCT segment
dbsn = 'PCT' # Output segment name
dbsd = 'PCT for showing results of icemap classification' # Output segment description
pctform = 'ATT' # PCT text format
tfile = pct2use # PCT text file name
nseg = pctread(ifile, dbpct, dbsn, dbsd, pctform, tfile)
logging.info("Export classification to TIF file")
# Export classification to TIF file
fili = tmpfile # Input file name
filo = outfile # Output file name
dbiw = [] # Raster input windows
dbic = chan_sieve2 # Input raster channel to export
dbib = [] # Input bitmap segment
dbvs = [] # Input vector segment
dblut = [] # Input LUT segment
dbpct = nseg # Input PCT segment
ftype = 'TIF' # Output file type
foptions = '' # Output file options
fexport(fili, filo, dbiw, dbic, dbib, dbvs, dblut, dbpct, ftype,
foptions)
except PCIException, e:
logger.exception(e.message)
return False
auxiliaryData = dataset.aux_data
qprintl('OK \\(^o^)/')
qprintl('Channels in dataset:')
for i in range(1, dataset.chan_count + 1):
qprintl(' Channel {}: {}'.format(i,
auxiliaryData.get_chan_description(i)))
# Create channels if not sufficient
qprintl('Is it neccessary to create a new channnel?')
if (dataset.chan_count < 9):
qprint(' Yes, creating new channel(s)...')
# pcimod: Channel Manager (Add/Delete)
from pci.pcimod import pcimod
pcimod(file=dataset.name,
pciop='ADD',
pcival=[9 - dataset.chan_count, 0, 0, 0])
dataset = datasource.open_dataset('data/golden_horseshoe.pix',
mode=datasource.eAM_WRITE)
auxiliaryData = dataset.aux_data
qprintl('OK \\(^o^)/')
qprintl('Channels in dataset:')
for i in range(1, dataset.chan_count + 1):
qprintl(' Channel {}: {}'.format(
i, auxiliaryData.get_chan_description(i)))
else:
qprintl(' No')
# KCLUS
# kclus: Unsupervised Classification with K-Means
fili_ref=os.path.join(input_dir,"prevndvi.pix"),
dbic_ref=[1],
filo=change_image,
algo="INTENRATIO")
print('Extract change as polygons')
expolras(fili=change_image,
dbic=[4],
thrtype="PixelValue",
tval=[90],
areaval=[100],
filo=change_image)
print('Convert the polygons to a bitmap')
poly2bit(fili=change_image,
dbvs=[2],
filo=change_image)
print('Add a new channel')
pcimod(file=change_image,
pciop="ADD",
pcival=[1,0,0,0])
print('Encode bitmap into an empty image channel')
bit_encode(file=change_image,
dbib=[3],
valu=[1],
dboc=[5])
def classification(image):
# Set timer
start = time.time()
# Define output file name
outputFile = "GH_classPolygons.shp"
output = outputFolder + "\\" + outputFile
# get image statistics to extract channel number
print "Detecting current channels..."
with ds.open_dataset(image) as dataset:
chansCount = dataset.chan_count
print str(chansCount) + " channels detected"
print ""
# Whipe previously created channels (only use if you want a fresh clean input file and don't need previously created channels)
chansDel = range(7, chansCount + 1)
if chansCount > 6: # Adjust depending on image bands
pcimod(file=image, pciop='del', pcival=chansDel)
print str(len(chansDel)) + " previously created channels deleted"
# Whipe previously created shape files in output folder
files = glob.glob(outputFolder + "\\" + '*')
for f in files:
os.remove(f)
print "Previous output files deleted"
print ""
# Count input channels and create input channel list
with ds.open_dataset(image) as dataset:
inputChansCount = dataset.chan_count
inputChans = range(1, inputChansCount + 1)
print inputChans
# Add 3 channels to the image for storing algorithm output
print "Adding three 8-bit channels to image..."
pcimod(file=image, pciop='add', pcival=[3, 0, 0, 0, 0, 0])
print "Three 8-bit channels added"
print ""
# Run k-means cluster algorithm
classesNumber = [8] # define number of classes
iterations = [10] # define number iterations
moveThresh = [0.01] # define move threshhold
print "Running unsupervized k-means classification..."
print "Creating " + str(classesNumber) + " classes, applying " + str(
iterations) + " iterations at a move-threshhold of " + str(moveThresh)
kclus(file=image,
dbic=inputChans,
dboc=[7],
numclus=classesNumber,
maxiter=iterations,
movethrs=moveThresh)
flag1 = time.time()
print "Classification complete! Time ellapsed: " + str(flag1 -
start) + " seconds"
print ""
# Run mode filter
print "Running Mode Filter..."
fmo(file=image, dbic=[7], dboc=[8], thinline="OFF", flsz=[3, 3])
flag2 = time.time()
print "Filtering complete! Time ellapsed: " + str(flag2 -
start) + " seconds"
print ""
# Run sieve
print "Applying sieve..."
sieve(file=image, dbic=[8], dboc=[9], sthresh=[16])
flag3 = time.time()
print "Sieve complete! Time ellapsed: " + str(flag3 - start) + " seconds"
print ""
# Create vector ploygons and export as shape file
print "Creating polygons..."
ras2poly(fili=image, dbic=[9], filo=output, ftype="SHP")
flag4 = time.time()
print "Polygons created! Time ellapsed: " + str(flag4 - start) + " seconds"
print ""
print "Exporting as shape file..."
end = time.time()
print "Total time ellapsed: " + str(end - start) + " seconds"
from pci.lut import lut
from pci.rgb import rgb
#Add new image channels to existing file
print(
"Pix file must be set up as Channel 1: SPOT Pan June 4, 1985 \nChannel 2-5: TM Band 1-4"
)
print("Put the correct pix file path into new_file")
# Input version
# new_file = input("Enter file path: ")
# new_file = r"{}".format(new_file)
new_file = r"C:\PCI Geomatics\OakRidgesV1.pix" # File location, reset to local path
channels = [7] #add 7 8bit channels for analysis
# Adding new channels
pcimod(file=new_file, pciop="ADD", pcival=channels)
file = new_file
dbic = [5, 4, 3] # Input RGB channels
dboc = [6, 7, 8] # Output IHS channels
dbiw = [] # Input Window - Optional
ihsmodel = "CYLINDER"
ihs(file, dbic, dboc, dbiw, ihsmodel)
# Empty variables indicate optional variables as indicated from documentation
func = "MATC" # Enhancement function
dbic = [1] # Input raster channel(s)
dblut = []
dbsn = "SPOT" # Segment name
dbsd = "SPOT Matched to Intensity" # Output LUT segment description
def processing(path, image):
print ""
print "Classifying " + str(image)
print ""
# Set timer
start = time.time()
# Define input/output file names
file_name, ext = os.path.splitext(str(image))
outputFile = file_name + "_classified.shp"
output = outputFolder + "\\" + outputFile
inputfile = path + image
# Whipe previously created shape files in output folder
files = glob.glob(outputFolder + "\\" + '*')
for f in files:
f_name, ext = os.path.splitext(str(os.path.basename(f)))
if file_name in f_name:
os.remove(f)
print str(f) + " deleted"
print ""
# get image statistics to extract channel number
print "Detecting current channels..."
with ds.open_dataset(inputfile) as dataset:
chansCount = dataset.chan_count
print str(chansCount) + " channels detected"
print ""
# Whipe previously created channels (only use if you want a fresh clean input file and don't need previously created channels)
chansDel = range(10, chansCount + 1)
if chansCount > 9: # Adjust depending on image bands
pcimod(file=inputfile, pciop='del', pcival=chansDel)
print str(len(chansDel)) + " previously created channels deleted"
# Redefine chansCount
with ds.open_dataset(inputfile) as dataset:
chansCount = dataset.chan_count
# Count input channels and create input channel list
with ds.open_dataset(inputfile) as dataset:
inputChansCount = dataset.chan_count
inputChans = range(
1, 8) # Define input channels (eg: (1,7)=channel 1 to channel 6))
print "Input channels: " + str(inputChans)
# k-means cluster algorithm
def classification(data):
# Add channel
pcimod(file=inputfile, pciop='add', pcival=[0, 0, 1, 0, 0, 0])
# Define input parameters
classesNumber = [8] # define number of classes
iterations = [10] # define number iterations
moveThresh = [0.01] # define move threshhold
print "Running unsupervized k-means classification..."
print "Creating " + str(classesNumber) + " classes, applying " + str(
iterations) + " iterations at a move-threshhold of " + str(
moveThresh)
# Run algorithm and create classification report
try:
Report.clear()
enableDefaultReport(report)
kclus(file=inputfile,
dbic=inputChans,
dboc=[chansCount + 1],
numclus=classesNumber,
maxiter=iterations,
movethrs=moveThresh)
finally:
enableDefaultReport('term') # this will close the report file
flag1 = time.time()
print "Classification complete! Time elapsed: " + str(
flag1 - start) + " seconds"
print ""
# Mode filter
def FMO(data):
# Add channel
pcimod(file=inputfile, pciop='add', pcival=[0, 0, 1, 0, 0, 0])
print "Running Mode Filter..."
filter = [5, 5]
# Run algorithm
fmo(file=inputfile,
dbic=[chansCount + 1],
dboc=[chansCount + 2],
thinline="OFF",
flsz=filter)
flag2 = time.time()
print "Filtering complete! Time elapsed: " + str(flag2 -
start) + " seconds"
print ""
# Sieve
def SIEVE(data):
# Add channel
pcimod(file=inputfile, pciop='add', pcival=[0, 0, 1, 0, 0, 0])
print "Applying sieve..."
# Run algorithm
sieve(file=inputfile,
dbic=[chansCount + 2],
dboc=[chansCount + 3],
sthresh=[32])
flag3 = time.time()
print "Sieve complete! Time elapsed: " + str(flag3 -
start) + " seconds"
print ""
# Create vector ploygons and export as shape file
def RAS2POLY(data):
print "Creating polygons..."
ras2poly(fili=inputfile,
dbic=[chansCount + 3],
filo=output,
ftype="SHP")
flag4 = time.time()
print "Polygons created! Time elapsed: " + str(flag4 -
start) + " seconds"
print ""
print "Exporting as shape file..."
classification(image)
FMO(image)
SIEVE(image)
RAS2POLY(image)
end = time.time()
print "Processing time elapsed for " + image + ": " + str(
end - start) + " seconds"
print ""