def predictSuperPixelLabels(classifier, image,numberSuperPixels, \
superPixelCompactness, makeProbabilities ):
print "\n**Computing super pixel labelling for input image"
outProbs = None
# Get superpixels
spgraph = superPixels.computeSuperPixelGraph(image,'slic',[numberSuperPixels, superPixelCompactness])
imgSuperPixelsMask = spgraph.m_labels
imgSuperPixels = spgraph.m_nodes
numberImgSuperPixels = len(imgSuperPixels)
print "**Image contains", numberImgSuperPixels, "superpixels"
# Get superpixel features
# todo: replace with features.computeSuperPixelFeatures JRS
superPixelFeatures = FeatureGenerator.generateSuperPixelFeatures(image, imgSuperPixelsMask, None)
assert np.shape(superPixelFeatures)[0] == numberImgSuperPixels, "Number of superpixels in feature array != number super pixels in image!:: " + str(np.shape(superPixelFeatures)[0]) + " vs. " + str(numberImgSuperPixels)
superPixelLabels = classifier.predict( superPixelFeatures )
if makeProbabilities:
outProbs = classification.classProbsOfFeatures(
superPixelFeatures, classifier, requireAllClasses=False
)
return (superPixelLabels, spgraph, outProbs)
def getSuperPixelData(msrcImages,numberSuperPixels, superPixelCompactness):
# Should probably make this a call to pomio in case the ordering changes in the future...
voidClassLabel = pomio.getVoidIdx()
numberImages = len(msrcImages)
# for each image:
# determine superpixel label (discard if void)
# compute superpixel features of valid superpixels
# append features to cumulative array of all super pixel features
# append label to array of all labels
superPixelFeatures = None
superPixelLabels = np.array([], int) # used for superpixel labels
numberVoidSuperPixels = 0 # keep track of void superpixels
nbClasses = pomio.getNumClasses()
classAdjCounts = np.zeros( (nbClasses, nbClasses) )
adjCountsTotal = 0
adjVoidCountsTotal = 0
for imgIdx in range(0, numberImages):
superPixelIgnoreList = np.array([], int) # this is used to skip over the superpixel in feature processing
print "\n**Processing Image#" , (imgIdx + 1) , " of" , numberImages
# get raw image and ground truth labels
img = msrcImages[imgIdx].m_img
imgPixelLabels = msrcImages[imgIdx].m_gt
# create superpixel map and graph for image
spgraph = superPixels.computeSuperPixelGraph( img, 'slic', [numberSuperPixels, superPixelCompactness] )
imgSuperPixelMask = spgraph.m_labels
imgSuperPixels = spgraph.m_nodes
numberImgSuperPixels = spgraph.getNumSuperPixels()
# create superpixel exclude list & superpixel label array
allSPClassLabels = []
for spIdx in range(0, numberImgSuperPixels):
superPixelValue = imgSuperPixels[spIdx]
#print "\tINFO: Processing superpixel =", superPixelValue , " of" , numberImgSuperPixels, " in image"
# Assume superpixel labels are sequence of integers
superPixelValueMask = (imgSuperPixelMask == superPixelValue ) # Boolean array for indexing superpixel-pixels
superPixelLabel = assignClassLabelToSuperPixel(superPixelValueMask, imgPixelLabels)
allSPClassLabels.append( superPixelLabel)
if(superPixelLabel == voidClassLabel):
# add to ignore list, increment void count & do not add to superpixel label array
superPixelIgnoreList = np.append(superPixelIgnoreList, superPixelValue)
numberVoidSuperPixels = numberVoidSuperPixels + 1
else:
superPixelLabels = np.append(superPixelLabels, superPixelLabel)
assert len(allSPClassLabels) == numberImgSuperPixels
(theseClassAdjCounts,adjVoidCount,adjCount) = spgraph.countClassAdjacencies( nbClasses, allSPClassLabels )
classAdjCounts += theseClassAdjCounts
adjCountsTotal += adjCount
adjVoidCountsTotal += adjVoidCount
# Now we have the superpixel labels, and an ignore list of void superpixels - time to get the features!
# todo: replace with features.computeSuperPixelFeatures JRS
imgSuperPixelFeatures = FeatureGenerator.generateSuperPixelFeatures(img, imgSuperPixelMask, excludeSuperPixelList=superPixelIgnoreList)
if superPixelFeatures == None:
superPixelFeatures = imgSuperPixelFeatures;
else:
# stack the superpixel features into a single list
superPixelFeatures = np.vstack( [ superPixelFeatures, imgSuperPixelFeatures ] )
assert np.shape(superPixelFeatures)[0] == np.shape(superPixelFeatures)[0] , "Number of samples != number labels"
print "\n**Processed total of" , numberImages, "images"
print " %d out of %d adjacencies were ignored due to void (%.2f %%)" % \
(adjVoidCountsTotal, adjCountsTotal, \
100.0*adjVoidCountsTotal/adjCountsTotal)
# Now return the results
return [ superPixelFeatures, superPixelLabels, classAdjCounts ]
colourMap = pomio.msrc_classToRGB
else:
spix, classProbs = isprs.loadISPRSResultFromMatlab(args.infile)
colourMap = isprs.colourMap
else:
# Assume input image needs processing and classifying
print "Superpixel generation mode"
numberSuperPixels = args.nbSuperPixels
superPixelCompactness = args.superPixelCompactness
imgRGB = amntools.readImage(args.infile)
# Turn image into superpixels.
spix = superPixels.computeSuperPixelGraph(
imgRGB, 'slic', [numberSuperPixels, superPixelCompactness])
print 'Loading classifier...'
assert args.clfrFn != None, 'No classifier filename specified!'
clfr = pomio.unpickleObject(args.clfrFn)
print 'Computing superpixel features...'
ftrs = features.computeSuperPixelFeatures(imgRGB,
spix,
ftype='classic',
aggtype='classic')
print 'Computing class probabilities...'
classProbs = classification.classProbsOfFeatures(ftrs,clfr,\
requireAllClasses=False)
from matplotlib import pyplot as plt
from matplotlib import cm
import pomio
import slic
import superPixels
import skimage
import isprs
import amntools
imgRGB = amntools.readImage(args.imagefile)
if len(args.spfile) == 0:
numberSuperPixels = args.nbSuperPixels
superPixelCompactness = args.superPixelCompactness
# Turn image into superpixels.
spix = superPixels.computeSuperPixelGraph(imgRGB, "slic", [numberSuperPixels, superPixelCompactness])
elif args.spfile.endswith(".pkl"):
superPixelInput = pomio.unpickleObject(args.spfile)
spix = superPixelInput[0]
classProbs = superPixelInput[1]
colourMap = pomio.msrc_classToRGB
elif args.spfile.endswith(".mat"):
spix, classProbs = isprs.loadISPRSResultFromMatlab(args.spfile)
colourMap = isprs.colourMap
else:
assert False
# Display superpixel boundaries on image.
plt.imshow(superPixels.generateImageWithSuperPixelBoundaries(imgRGB, spix.m_labels))
plt.show()
#infile = args.infile
#outfile = args.outfile
#outprobsfile = args.outprobsfile
numberSuperPixels = args.nbSuperPixels
superPixelCompactness = args.superPixelCompactness
if args.verbose:
plt.interactive(1)
plt.figure()
pomio.showClassColours()
plt.figure()
print 'Classifying file ', args.infile
image = amntools.readImage(args.infile)
spGraph = superPixels.computeSuperPixelGraph(
image, 'slic', [numberSuperPixels, superPixelCompactness])
[spClassPreds, spClassProbs
] = classification.classifyImageSuperPixels(image, clfr, spGraph, ftype,
aggtype, makeProbs)
spClassPredsImage = spGraph.imageFromSuperPixelData(
spClassPreds.reshape((len(spClassPreds), 1)))
if args.verbose:
plt.subplot(1, 2, 1)
plt.imshow(image)
plt.title(args.infile)
plt.subplot(1, 2, 2)
pomio.showLabels(spClassPredsImage)
plt.waitforbuttonpress()
if args.outfile and len(args.outfile) > 0:
#infile = args.infile
#outfile = args.outfile
#outprobsfile = args.outprobsfile
numberSuperPixels = args.nbSuperPixels
superPixelCompactness = args.superPixelCompactness
if args.verbose:
plt.interactive(1)
plt.figure()
pomio.showClassColours()
plt.figure()
print 'Classifying file ', args.infile
image = amntools.readImage(args.infile)
spGraph = superPixels.computeSuperPixelGraph(image,'slic',[numberSuperPixels, superPixelCompactness])
[spClassPreds, spClassProbs] = classification.classifyImageSuperPixels( image, clfr, spGraph, ftype, aggtype, makeProbs)
spClassPredsImage = spGraph.imageFromSuperPixelData( spClassPreds.reshape( (len(spClassPreds),1) ) )
if args.verbose:
plt.subplot(1,2,1)
plt.imshow(image)
plt.title(args.infile)
plt.subplot(1,2,2)
pomio.showLabels(spClassPredsImage)
plt.waitforbuttonpress()
if args.outfile and len(args.outfile)>0:
print 'Writing output label file %s' % args.outfile
outimg = pomio.msrc_convertLabelsToRGB( spClassPredsImage )
skimage.io.imsave(args.outfile, outimg)
