Merge pull request #32 from jlaura/subpixel (8e862b85) · Commits · aflab / astrogeology / Autocnet

.travis.yml

+6 −4

Changes for .travis.yml: 6 added lines, 4 removed lines.
Original line number	Diff line number	Diff line
		@@ -27,13 +27,15 @@ install:
		- conda info -a

		# Create a virtual env and install dependencies
		- conda create -y -q -n test-env python=$TRAVIS_PYTHON_VERSION nose gdal numpy pillow scipy pandas networkx scikit-image
		- conda create -y -q -n test-env python=$TRAVIS_PYTHON_VERSION nose numpy pillow scipy pandas networkx scikit-image
		# Activate the env
		- source activate test-env

		# Install the non-conda packages if required, requirements.txt duplicates are ignored
		- conda install -c https://conda.anaconda.org/jlaura opencv3=3.0.0
		- conda install -c https://conda.anaconda.org/osgeo gdal
		- conda install -c osgeo proj4
		- conda upgrade numpy
		- pip install -r requirements.txt
		- pip install coverage
		- pip install coveralls
		@@ -41,6 +43,9 @@ install:
		script:
		- nosetests --with-coverage --cover-package=autocnet

		after_success:
		- coveralls

		notifications:
		email:
		recipients:
		@@ -50,6 +55,3 @@ notifications:
		- jwbacker@usgs.gov
		on_success: always
		on_failure: always
		No newline at end of file

		after_success:
		- coveralls

autocnet/fileio/io_gdal.py

+4 −2

Changes for autocnet/fileio/io_gdal.py: 4 added lines, 2 removed lines.
Original line number	Diff line number	Diff line
		import os

		import numpy as np
		from osgeo import gdal
		from osgeo import osr
		import gdal
		import osr

		from autocnet.fileio import extract_metadata

		gdal.UseExceptions()

		NP2GDAL_CONVERSION = {
		"uint8": 1,
		"int8": 1,

autocnet/graph/network.py

+73 −18

Changes for autocnet/graph/network.py: 73 added lines, 18 removed lines.
Original line number	Diff line number	Diff line
		@@ -258,7 +258,6 @@ class CandidateGraph(nx.Graph):

		transformation_matrix, ransac_mask = od.compute_homography(s_coords,
		d_coords)

		ransac_mask = ransac_mask.ravel()
		# Convert the truncated RANSAC mask back into a full length mask
		if clean_keys:
		@@ -266,34 +265,78 @@ class CandidateGraph(nx.Graph):
		else:
		mask = ransac_mask

		# Compute the error in the homography
		s_trans = np.hstack((s_coords[::-1],np.ones(s_coords.shape[0]).reshape(-1,1))).T
		s_trans = np.dot(transformation_matrix, s_trans).T

		#Normalize the error
		for i in range(3):
		s_trans[i] /= s_trans[2]

		d_trans = np.hstack((d_coords[::-1], np.ones(d_coords.shape[0]).reshape(-1,1)))

		attributes['homography_error'] = np.sqrt(np.sum((d_trans - s_trans)**2, axis=1))
		attributes['homography'] = transformation_matrix
		attributes['ransac'] = mask

		def compute_subpixel_offsets(self):
		def compute_subpixel_offsets(self, clean_keys=[], threshold=0.8, upsampling=10):
		"""
		For the entire graph, compute the subpixel offsets using pattern-matching and add the result
		as an attribute to each edge of the graph.

		Returns
		-------
		subpixel_offsets : ndarray
		A numpy array containing all the subpixel offsets for the entire graph.
		Parameters
		----------
		clean_keys : list
		of string keys to masking arrays
		(created by calling outlier detection)

		threshold : float
		On the range [-1, 1]. Values less than or equal to
		this threshold are masked and can be considered
		outliers
		"""
		subpixel_offsets = []
		for source, destination, attributes in self.edges_iter(data=True): #for each edge
		matches = attributes['matches'] #grab the matches

		for source, destination, attributes in self.edges_iter(data=True):
		matches = attributes['matches']

		full_offsets = np.zeros((len(matches), 3))

		# Build up a composite mask from all of the user specified masks
		if clean_keys:
		mask = np.prod([attributes[i] for i in clean_keys], axis=0, dtype=np.bool)
		matches = matches[mask]
		full_mask = np.where(mask == True)

		src_image = self.node[source]['image']
		dest_image = self.node[destination]['image']
		edge_offsets = []
		for i, (idx, row) in enumerate(matches.iterrows()): #for each edge, calculate this for each keypoint pair

		# Preallocate the numpy array to avoid appending and type conversion
		edge_offsets = np.empty((len(matches),3))

		# for each edge, calculate this for each keypoint pair
		for i, (idx, row) in enumerate(matches.iterrows()):
		s_idx = int(row['source_idx'])
		d_idx = int(row['destination_idx'])
		src_keypoint = self.node[source]['keypoints'][s_idx]
		dest_keypoint = self.node[destination]['keypoints'][d_idx]
		edge_offsets.append(sp.subpixel_offset(src_keypoint, dest_keypoint, src_image, dest_image))
		attributes['subpixel_offsets'] = np.array(edge_offsets)
		subpixel_offsets.append(np.array(edge_offsets))
		return subpixel_offsets

		# Compute the subpixel offset
		edge_offsets[i] = sp.subpixel_offset(src_keypoint, dest_keypoint, src_image, dest_image, upsampling=upsampling)

		# Compute the mask for correlations less than the threshold
		threshold_mask = edge_offsets[edge_offsets[:,-1] >= threshold]

		# Convert the truncated mask back into a full length mask
		if clean_keys:
		mask[full_mask] = threshold_mask
		full_offsets[full_mask] = edge_offsets
		else:
		mask = threshold_mask

		attributes['subpixel_offsets'] = pd.DataFrame(full_offsets, columns=['x_offset',
		'y_offset',
		'correlation'])
		attributes['subpixel'] = mask

		def to_cnet(self, clean_keys=[]):
		"""
		@@ -349,12 +392,15 @@ class CandidateGraph(nx.Graph):
		mask = np.prod([attributes[i] for i in clean_keys], axis=0, dtype=np.bool)
		matches = matches[mask]

		if 'subpixel' in clean_keys:
		offsets = attributes['subpixel_offsets'][attributes['subpixel']]
		print(offsets)
		kp1 = self.node[source]['keypoints']
		kp2 = self.node[destination]['keypoints']

		pt_idx = 0
		values = []
		for idx, row in matches.iterrows():
		for i, (idx, row) in enumerate(matches.iterrows()):
		# Composite matching key (node_id, point_id)
		m1 = (source, int(row['source_idx']))
		m2 = (destination, int(row['destination_idx']))
		@@ -365,8 +411,17 @@ class CandidateGraph(nx.Graph):
		pt_idx,
		source])

		values.append([kp2[m2[1]].pt[0],
		kp2[m2[1]].pt[1],
		kp2x = kp2[m2[1]].pt[0]
		kp2y = kp2[m2[1]].pt[1]

		if 'subpixel' in clean_keys:
		print(idx)
		print(kp2x, kp2y)
		kp2x += offsets['x_offset'].values[i]
		kp2y += offsets['y_offset'].values[i]
		print(kp2x, kp2y)
		values.append([kp2x,
		kp2y,
		m2,
		pt_idx,
		destination])

autocnet/graph/tests/test_network.py

+7 −5

Changes for autocnet/graph/tests/test_network.py: 7 added lines, 5 removed lines.
Original line number	Diff line number	Diff line
		@@ -13,8 +13,9 @@ from .. import network

		class TestCandidateGraph(unittest.TestCase):

		def setUp(self):
		self.graph = network.CandidateGraph.from_adjacency(get_path('adjacency.json'))
		@classmethod
		def setUpClass(cls):
		cls.graph = network.CandidateGraph.from_adjacency(get_path('adjacency.json'))

		def test_get_name(self):
		node_number = self.graph.node_name_map['AS15-M-0297_SML.png']
		@@ -28,6 +29,10 @@ class TestCandidateGraph(unittest.TestCase):
		def test_to_json_file(self):
		self.graph.to_json_file('test_graph_to_json.json')
		self.assertTrue(os.path.exists('test_graph_to_json.json'))
		try:
		os.remove('test_graph_to_json.json')
		except:
		pass

		def test_extract_features(self):
		# also tests get_geodataset() and get_keypoints
		@@ -42,7 +47,4 @@ class TestCandidateGraph(unittest.TestCase):
		self.assertEquals(self.graph.get_keypoints(node_number), node['keypoints'])

		def tearDown(self):
		try:
		os.remove('test_graph_to_json.json')
		except:
		pass

autocnet/matcher/outlier_detector.py

+2 −0

Changes for autocnet/matcher/outlier_detector.py: 2 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		@@ -148,3 +148,5 @@ def compute_homography(kp1, kp2, outlier_algorithm=cv2.RANSAC, reproj_threshold=
		reproj_threshold)
		mask = mask.astype(bool)
		return transformation_matrix, mask