Loading autocnet/examples/Apollo15/adjacency.json +25 −1 Original line number Diff line number Diff line {"AS15-M-0297_SML.png": ["AS15-M-0298_SML.png", "AS15-M-0300_SML.png", "AS15-M-0299_SML.png", "AS15-M-0296_SML.png"], "AS15-M-0300_SML.png": ["AS15-M-0298_SML.png", "AS15-M-0297_SML.png", "AS15-M-0299_SML.png"], "AS15-M-0299_SML.png": ["AS15-M-0298_SML.png", "AS15-M-0297_SML.png", "AS15-M-0300_SML.png", "AS15-M-0296_SML.png"], "AS15-M-0295_SML.png": [], "AS15-M-0296_SML.png": ["AS15-M-0298_SML.png", "AS15-M-0297_SML.png", "AS15-M-0299_SML.png"], "AS15-M-0298_SML.png": ["AS15-M-0297_SML.png", "AS15-M-0300_SML.png", "AS15-M-0299_SML.png", "AS15-M-0296_SML.png"]} No newline at end of file {"autocnet/examples/Apollo15/AS15-M-0297_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png", "autocnet/examples/Apollo15/AS15-M-0300_SML.png", "autocnet/examples/Apollo15/AS15-M-0299_SML.png", "autocnet/examples/Apollo15/AS15-M-0296_SML.png"], "autocnet/examples/Apollo15/AS15-M-0300_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png", "autocnet/examples/Apollo15/AS15-M-0297_SML.png", "autocnet/examples/Apollo15/AS15-M-0299_SML.png"], "autocnet/examples/Apollo15/AS15-M-0299_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png", "autocnet/examples/Apollo15/AS15-M-0297_SML.png", "autocnet/examples/Apollo15/AS15-M-0300_SML.png", "autocnet/examples/Apollo15/AS15-M-0296_SML.png"], "autocnet/examples/Apollo15/AS15-M-0295_SML.png" : [], "autocnet/examples/Apollo15/AS15-M-0296_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png", "autocnet/examples/Apollo15/AS15-M-0297_SML.png", "autocnet/examples/Apollo15/AS15-M-0299_SML.png"], "autocnet/examples/Apollo15/AS15-M-0298_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0297_SML.png", "autocnet/examples/Apollo15/AS15-M-0300_SML.png", "autocnet/examples/Apollo15/AS15-M-0299_SML.png", "autocnet/examples/Apollo15/AS15-M-0296_SML.png"]} autocnet/examples/Apollo15/two_image_adjacency.json +4 −2 Original line number Diff line number Diff line {"AS15-M-0297_SML.png": ["AS15-M-0298_SML.png"], "AS15-M-0298_SML.png": ["AS15-M-0297_SML.png"]} {"autocnet/examples/Apollo15/AS15-M-0297_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png"], "autocnet/examples/Apollo15/AS15-M-0298_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0297_SML.png"]} autocnet/graph/network.py +169 −34 Original line number Diff line number Diff line Loading @@ -2,10 +2,15 @@ import os import networkx as nx import pandas as pd import cv2 import numpy as np from scipy.misc import bytescale # store image array from autocnet.control.control import C from autocnet.fileio import io_json from autocnet.fileio.io_gdal import GeoDataset from autocnet.matcher import feature_extractor as fe # extract features from image class CandidateGraph(nx.Graph): """ Loading @@ -15,6 +20,12 @@ class CandidateGraph(nx.Graph): ---------- Attributes node_counter : int The number of nodes in the graph. node_name_map : dict The mapping of image labels (i.e. file base names) to their corresponding node indices. ---------- """ Loading @@ -22,47 +33,138 @@ class CandidateGraph(nx.Graph): super(CandidateGraph, self).__init__(*args, **kwargs) self.node_counter = 0 node_labels = {} self.node_name_map = {} # the node_name is the relative path for the image for node_name, node_attributes in self.nodes_iter(data=True): if os.path.isabs(node_name): node_attributes['image_name'] = os.path.basename(node_name) node_attributes['image_path'] = node_name else: node_attributes['image_name'] = node_name node_attributes['image_path'] = None node_attributes['image_name'] = os.path.basename(os.path.abspath(node_name)) node_attributes['image_path'] = os.path.abspath(node_name) node_labels[node_attributes['image_name']] = self.node_counter # fill the dictionary used for relabelling nodes with relative path keys node_labels[node_name] = self.node_counter # fill the dictionary used for mapping base name to node index self.node_name_map[node_attributes['image_name']] = self.node_counter self.node_counter += 1 nx.relabel_nodes(self, node_labels, copy=False) @classmethod def from_adjacency_file(cls, inputfile): """ Instantiate the class using an adjacency file. This file must contain relative or absolute paths to image files. Parameters ---------- inputfile : str The input file containing the graph representation Returns ------- : object A Network graph object Examples -------- >>> from autocnet.examples import get_path >>> inputfile = get_path('adjacency.json') >>> candidate_graph = network.CandidateGraph.from_adjacency_file(inputfile) """ adjacency_dict = io_json.read_json(inputfile) return cls(adjacency_dict) def get_name(self, nodeIndex): """ Get the image name for the given node. Parameters ---------- nodeIndex : int The index of the node. Returns ------- : str The name of the image attached to the given node. """ return self.node[nodeIndex]['image_name'] def get_keypoints(self, nodeIndex): """ Get the list of keypoints for the given node. Parameters ---------- nodeIndex : int The index of the node. Returns ------- : list The list of keypoints for the given node. """ return self.node[nodeIndex]['keypoints'] def add_image(self, *args, **kwargs): """ Adds an image node to the graph. Parameters ========== ---------- """ raise NotImplementedError self.add_node(self.node_counter, *args, **kwargs) #self.node_labels[self.node[self.node_counter]['image_name']] = self.node_counter self.node_counter += 1 def adjacency_to_json(self, outputfile): def get_geodataset(self, nodeIndex): """ Write the edge structure to a JSON adjacency list Constructs a GeoDataset object from the given node image and assigns the dataset and its NumPy array to the 'handle' and 'image' node attributes. Parameters ========== ---------- nodeIndex : int The index of the node. outputfile : str PATH where the JSON will be written """ adjacency_dict = {} for n in self.nodes(): adjacency_dict[n] = self.neighbors(n) io_json.write_json(adjacency_dict, outputfile) self.node[nodeIndex]['handle'] = GeoDataset(self.node[nodeIndex]['image_path']) self.node[nodeIndex]['image'] = bytescale(self.node[nodeIndex]['handle'].read_array()) def extract_features(self, nfeatures) : """ Extracts features from each image in the graph and uses the result to assign the node attributes for 'handle', 'image', 'keypoints', and 'descriptors'. Parameters ---------- nfeatures : int The number of features to be extracted. def add_matches(self, matches): """ # Loop through the nodes (i.e. images) on the graph and fill in their attributes. # These attributes are... # geo dataset (handle and image) # features (keypoints and descriptors) for node, attributes in self.nodes_iter(data=True): self.get_geodataset(node) extraction_params = {'nfeatures' : nfeatures} attributes['keypoints'], attributes['descriptors'] = fe.extract_features(attributes['image'], extraction_params) def add_matches(self, matches): """ Adds match data to a node and attributes the data to the appropriate edges, e.g. if A-B have a match, edge A-B is attributes with the pandas dataframe. Loading @@ -75,7 +177,6 @@ class CandidateGraph(nx.Graph): matches : dataframe The pandas dataframe containing the matches """ source_groups = matches.groupby('source_image') for i, source_group in source_groups: for j, dest_group in source_group.groupby('destination_image'): Loading @@ -92,6 +193,49 @@ class CandidateGraph(nx.Graph): else: edge['matches'] = dest_group def compute_homography(self, source_key, destination_key, outlier_algorithm=cv2.RANSAC): """ Parameters ---------- source_key : str The identifier for the source node destination_key : str The identifier for the destination node Returns ------- : tuple A tuple of the form (transformation matrix, bad entry mask) The returned tuple is empty if there is no edge between the source and destination nodes or if it exists, but has not been populated with a matches dataframe. """ if self.has_edge(source_key, destination_key): try: edge = self[source_key][destination_key] except: edge = self[destination_key][source_key] if 'matches' in edge.keys(): source_keypoints = [] destination_keypoints = [] for i, row in edge['matches'].iterrows(): source_idx = row['source_idx'] src_keypoint = [self.node[source_key]['keypoints'][int(source_idx)].pt[0], self.node[source_key]['keypoints'][int(source_idx)].pt[1]] destination_idx = row['destination_idx'] dest_keypoint = [self.node[destination_key]['keypoints'][int(destination_idx)].pt[0], self.node[destination_key]['keypoints'][int(destination_idx)].pt[1]] source_keypoints.append(src_keypoint) destination_keypoints.append(dest_keypoint) return cv2.findHomography(np.array(source_keypoints), np.array(destination_keypoints), outlier_algorithm, 5.0) else: return ('', '') else: return ('','') def to_cnet(self): """ Generate a control network (C) object from a graph Loading Loading @@ -154,28 +298,19 @@ class CandidateGraph(nx.Graph): return merged_cnet @classmethod def from_adjacency(cls, inputfile): def to_json_file(self, outputfile): """ Instantiate the class using an adjacency list Write the edge structure to a JSON adjacency list Parameters ---------- inputfile : str The input file containing the graph representation Returns ------- : object A Network graph object ========== Examples -------- >>> from autocnet.examples import get_path >>> inputfile = get_path('adjacency.json') >>> candidate_graph = network.CandidateGraph.from_adjacency(inputfile) outputfile : str PATH where the JSON will be written """ adjacency_dict = io_json.read_json(inputfile) return cls(adjacency_dict) adjacency_dict = {} for n in self.nodes(): adjacency_dict[n] = self.neighbors(n) io_json.write_json(adjacency_dict, outputfile) autocnet/graph/tests/test_network.py +30 −10 Original line number Diff line number Diff line import os import sys sys.path.insert(0, os.path.abspath('..')) import cv2 import numpy as np import unittest from autocnet.examples import get_path import sys sys.path.insert(0, os.path.abspath('..')) from .. import network class TestCandidateGraph(unittest.TestCase): def setUp(self): self.graph = network.CandidateGraph.from_adjacency(get_path('adjacency.json')) self.graph = network.CandidateGraph.from_adjacency_file(get_path('adjacency.json')) def test_get_name(self): node_number = self.graph.node_name_map['AS15-M-0297_SML.png'] name = self.graph.get_name(node_number) self.assertEquals(name, 'AS15-M-0297_SML.png') def test_add_image(self): with self.assertRaises(NotImplementedError): self.graph.add_image() self.assertEqual(self.graph.node_counter, 7) def test_adjacency_to_json(self): self.graph.adjacency_to_json('test_adjacency_to_json.json') self.assertTrue(os.path.exists('test_adjacency_to_json.json')) 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')) def test_extract_features(self): # also tests get_geodataset() and get_keypoints self.graph.extract_features(10) node_number = self.graph.node_name_map['AS15-M-0297_SML.png'] node = self.graph.node[node_number] self.assertEquals(len(node['image']), 1012) self.assertEquals(len(node['keypoints']), 10) self.assertEquals(len(node['descriptors']), 10) self.assertIsInstance(node['keypoints'][0], type(cv2.KeyPoint())) self.assertIsInstance(node['descriptors'][0], np.ndarray) self.assertEquals(self.graph.get_keypoints(node_number), node['keypoints']) def tearDown(self): try: os.remove('test_adjacency_to_json.json') os.remove('test_graph_to_json.json') except: pass autocnet/matcher/matcher.py +100 −0 Original line number Diff line number Diff line Loading @@ -169,3 +169,103 @@ class FlannMatcher(object): 'destination_image', 'destination_idx', 'distance']) class OutlierDetector(object): """ A class which contains several outlier detection methods which all return True/False masks as pandas data series, which can be used as masks for the "matches" pandas dataframe which stores match information for each edge of the graph. Attributes ---------- """ def __init__(self): pass # (query only takes care of literal self-matches on a keypoint basis, not self-matches for the whole image) def self_neighbors(self, matches): """ Returns a pandas data series intended to be used as a mask. Each row is True if it is not matched to a point in the same image (good) and False if it is (bad.) Parameters ---------- matches : dataframe the matches dataframe stored along the edge of the graph containing matched points with columns containing: matched image name, query index, train index, and descriptor distance Returns ------- : dataseries Intended to mask the matches dataframe. True means the row is not matched to a point in the same image and false the row is. """ return matches.source_image != matches.destination_image def distance_ratio(self, matches, ratio=0.8): """ Compute and return a mask for the matches dataframe stored on each edge of the graph using the ratio test and distance_ratio set during initialization. Parameters ---------- matches : dataframe the matches dataframe stored along the edge of the graph containing matched points with columns containing: matched image name, query index, train index, and descriptor distance. ***Will only work as expected if matches already has dropped duplicates*** ratio: float the ratio between the first and second-best match distances for each keypoint to use as a bound for marking the first keypoint as "good." Returns ------- : dataseries Intended to mask the matches dataframe. Rows are True if the associated keypoint passes the ratio test and false otherwise. Keypoints without more than one match are True by default, since the ratio test will not work for them. """ #0.8 is Lowe's paper value -- can be changed. mask = [] temp_matches = matches.drop_duplicates() #don't want to deal with duplicates... for key, group in temp_matches.groupby('source_idx'): #won't work if there's only 1 match for each queryIdx if len(group) < 2: mask.append(True) else: if group['distance'].iloc[0] < ratio * group['distance'].iloc[1]: #this means distance _0_ is good and can drop all other distances mask.append(True) for i in range(len(group['distance']-1)): mask.append(False) else: for i in range(len(group['distance'])): mask.append(False) return pd.Series(mask) def mirroring_test(self, matches): """ Compute and return a mask for the matches dataframe on each edge of the graph which will keep only entries in which there is both a source -> destination match and a destination -> source match. Parameters ---------- matches : dataframe the matches dataframe stored along the edge of the graph containing matched points with columns containing: matched image name, query index, train index, and descriptor distance Returns ------- : dataseries Intended to mask the matches dataframe. Rows are True if the associated keypoint passes the mirroring test and false otherwise. That is, if 1->2, 2->1, both rows will be True, otherwise, they will be false. Keypoints with only one match will be False. Removes duplicate rows. """ return matches.duplicated(keep='first') Loading
autocnet/examples/Apollo15/adjacency.json +25 −1 Original line number Diff line number Diff line {"AS15-M-0297_SML.png": ["AS15-M-0298_SML.png", "AS15-M-0300_SML.png", "AS15-M-0299_SML.png", "AS15-M-0296_SML.png"], "AS15-M-0300_SML.png": ["AS15-M-0298_SML.png", "AS15-M-0297_SML.png", "AS15-M-0299_SML.png"], "AS15-M-0299_SML.png": ["AS15-M-0298_SML.png", "AS15-M-0297_SML.png", "AS15-M-0300_SML.png", "AS15-M-0296_SML.png"], "AS15-M-0295_SML.png": [], "AS15-M-0296_SML.png": ["AS15-M-0298_SML.png", "AS15-M-0297_SML.png", "AS15-M-0299_SML.png"], "AS15-M-0298_SML.png": ["AS15-M-0297_SML.png", "AS15-M-0300_SML.png", "AS15-M-0299_SML.png", "AS15-M-0296_SML.png"]} No newline at end of file {"autocnet/examples/Apollo15/AS15-M-0297_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png", "autocnet/examples/Apollo15/AS15-M-0300_SML.png", "autocnet/examples/Apollo15/AS15-M-0299_SML.png", "autocnet/examples/Apollo15/AS15-M-0296_SML.png"], "autocnet/examples/Apollo15/AS15-M-0300_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png", "autocnet/examples/Apollo15/AS15-M-0297_SML.png", "autocnet/examples/Apollo15/AS15-M-0299_SML.png"], "autocnet/examples/Apollo15/AS15-M-0299_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png", "autocnet/examples/Apollo15/AS15-M-0297_SML.png", "autocnet/examples/Apollo15/AS15-M-0300_SML.png", "autocnet/examples/Apollo15/AS15-M-0296_SML.png"], "autocnet/examples/Apollo15/AS15-M-0295_SML.png" : [], "autocnet/examples/Apollo15/AS15-M-0296_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png", "autocnet/examples/Apollo15/AS15-M-0297_SML.png", "autocnet/examples/Apollo15/AS15-M-0299_SML.png"], "autocnet/examples/Apollo15/AS15-M-0298_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0297_SML.png", "autocnet/examples/Apollo15/AS15-M-0300_SML.png", "autocnet/examples/Apollo15/AS15-M-0299_SML.png", "autocnet/examples/Apollo15/AS15-M-0296_SML.png"]}
autocnet/examples/Apollo15/two_image_adjacency.json +4 −2 Original line number Diff line number Diff line {"AS15-M-0297_SML.png": ["AS15-M-0298_SML.png"], "AS15-M-0298_SML.png": ["AS15-M-0297_SML.png"]} {"autocnet/examples/Apollo15/AS15-M-0297_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0298_SML.png"], "autocnet/examples/Apollo15/AS15-M-0298_SML.png" : ["autocnet/examples/Apollo15/AS15-M-0297_SML.png"]}
autocnet/graph/network.py +169 −34 Original line number Diff line number Diff line Loading @@ -2,10 +2,15 @@ import os import networkx as nx import pandas as pd import cv2 import numpy as np from scipy.misc import bytescale # store image array from autocnet.control.control import C from autocnet.fileio import io_json from autocnet.fileio.io_gdal import GeoDataset from autocnet.matcher import feature_extractor as fe # extract features from image class CandidateGraph(nx.Graph): """ Loading @@ -15,6 +20,12 @@ class CandidateGraph(nx.Graph): ---------- Attributes node_counter : int The number of nodes in the graph. node_name_map : dict The mapping of image labels (i.e. file base names) to their corresponding node indices. ---------- """ Loading @@ -22,47 +33,138 @@ class CandidateGraph(nx.Graph): super(CandidateGraph, self).__init__(*args, **kwargs) self.node_counter = 0 node_labels = {} self.node_name_map = {} # the node_name is the relative path for the image for node_name, node_attributes in self.nodes_iter(data=True): if os.path.isabs(node_name): node_attributes['image_name'] = os.path.basename(node_name) node_attributes['image_path'] = node_name else: node_attributes['image_name'] = node_name node_attributes['image_path'] = None node_attributes['image_name'] = os.path.basename(os.path.abspath(node_name)) node_attributes['image_path'] = os.path.abspath(node_name) node_labels[node_attributes['image_name']] = self.node_counter # fill the dictionary used for relabelling nodes with relative path keys node_labels[node_name] = self.node_counter # fill the dictionary used for mapping base name to node index self.node_name_map[node_attributes['image_name']] = self.node_counter self.node_counter += 1 nx.relabel_nodes(self, node_labels, copy=False) @classmethod def from_adjacency_file(cls, inputfile): """ Instantiate the class using an adjacency file. This file must contain relative or absolute paths to image files. Parameters ---------- inputfile : str The input file containing the graph representation Returns ------- : object A Network graph object Examples -------- >>> from autocnet.examples import get_path >>> inputfile = get_path('adjacency.json') >>> candidate_graph = network.CandidateGraph.from_adjacency_file(inputfile) """ adjacency_dict = io_json.read_json(inputfile) return cls(adjacency_dict) def get_name(self, nodeIndex): """ Get the image name for the given node. Parameters ---------- nodeIndex : int The index of the node. Returns ------- : str The name of the image attached to the given node. """ return self.node[nodeIndex]['image_name'] def get_keypoints(self, nodeIndex): """ Get the list of keypoints for the given node. Parameters ---------- nodeIndex : int The index of the node. Returns ------- : list The list of keypoints for the given node. """ return self.node[nodeIndex]['keypoints'] def add_image(self, *args, **kwargs): """ Adds an image node to the graph. Parameters ========== ---------- """ raise NotImplementedError self.add_node(self.node_counter, *args, **kwargs) #self.node_labels[self.node[self.node_counter]['image_name']] = self.node_counter self.node_counter += 1 def adjacency_to_json(self, outputfile): def get_geodataset(self, nodeIndex): """ Write the edge structure to a JSON adjacency list Constructs a GeoDataset object from the given node image and assigns the dataset and its NumPy array to the 'handle' and 'image' node attributes. Parameters ========== ---------- nodeIndex : int The index of the node. outputfile : str PATH where the JSON will be written """ adjacency_dict = {} for n in self.nodes(): adjacency_dict[n] = self.neighbors(n) io_json.write_json(adjacency_dict, outputfile) self.node[nodeIndex]['handle'] = GeoDataset(self.node[nodeIndex]['image_path']) self.node[nodeIndex]['image'] = bytescale(self.node[nodeIndex]['handle'].read_array()) def extract_features(self, nfeatures) : """ Extracts features from each image in the graph and uses the result to assign the node attributes for 'handle', 'image', 'keypoints', and 'descriptors'. Parameters ---------- nfeatures : int The number of features to be extracted. def add_matches(self, matches): """ # Loop through the nodes (i.e. images) on the graph and fill in their attributes. # These attributes are... # geo dataset (handle and image) # features (keypoints and descriptors) for node, attributes in self.nodes_iter(data=True): self.get_geodataset(node) extraction_params = {'nfeatures' : nfeatures} attributes['keypoints'], attributes['descriptors'] = fe.extract_features(attributes['image'], extraction_params) def add_matches(self, matches): """ Adds match data to a node and attributes the data to the appropriate edges, e.g. if A-B have a match, edge A-B is attributes with the pandas dataframe. Loading @@ -75,7 +177,6 @@ class CandidateGraph(nx.Graph): matches : dataframe The pandas dataframe containing the matches """ source_groups = matches.groupby('source_image') for i, source_group in source_groups: for j, dest_group in source_group.groupby('destination_image'): Loading @@ -92,6 +193,49 @@ class CandidateGraph(nx.Graph): else: edge['matches'] = dest_group def compute_homography(self, source_key, destination_key, outlier_algorithm=cv2.RANSAC): """ Parameters ---------- source_key : str The identifier for the source node destination_key : str The identifier for the destination node Returns ------- : tuple A tuple of the form (transformation matrix, bad entry mask) The returned tuple is empty if there is no edge between the source and destination nodes or if it exists, but has not been populated with a matches dataframe. """ if self.has_edge(source_key, destination_key): try: edge = self[source_key][destination_key] except: edge = self[destination_key][source_key] if 'matches' in edge.keys(): source_keypoints = [] destination_keypoints = [] for i, row in edge['matches'].iterrows(): source_idx = row['source_idx'] src_keypoint = [self.node[source_key]['keypoints'][int(source_idx)].pt[0], self.node[source_key]['keypoints'][int(source_idx)].pt[1]] destination_idx = row['destination_idx'] dest_keypoint = [self.node[destination_key]['keypoints'][int(destination_idx)].pt[0], self.node[destination_key]['keypoints'][int(destination_idx)].pt[1]] source_keypoints.append(src_keypoint) destination_keypoints.append(dest_keypoint) return cv2.findHomography(np.array(source_keypoints), np.array(destination_keypoints), outlier_algorithm, 5.0) else: return ('', '') else: return ('','') def to_cnet(self): """ Generate a control network (C) object from a graph Loading Loading @@ -154,28 +298,19 @@ class CandidateGraph(nx.Graph): return merged_cnet @classmethod def from_adjacency(cls, inputfile): def to_json_file(self, outputfile): """ Instantiate the class using an adjacency list Write the edge structure to a JSON adjacency list Parameters ---------- inputfile : str The input file containing the graph representation Returns ------- : object A Network graph object ========== Examples -------- >>> from autocnet.examples import get_path >>> inputfile = get_path('adjacency.json') >>> candidate_graph = network.CandidateGraph.from_adjacency(inputfile) outputfile : str PATH where the JSON will be written """ adjacency_dict = io_json.read_json(inputfile) return cls(adjacency_dict) adjacency_dict = {} for n in self.nodes(): adjacency_dict[n] = self.neighbors(n) io_json.write_json(adjacency_dict, outputfile)
autocnet/graph/tests/test_network.py +30 −10 Original line number Diff line number Diff line import os import sys sys.path.insert(0, os.path.abspath('..')) import cv2 import numpy as np import unittest from autocnet.examples import get_path import sys sys.path.insert(0, os.path.abspath('..')) from .. import network class TestCandidateGraph(unittest.TestCase): def setUp(self): self.graph = network.CandidateGraph.from_adjacency(get_path('adjacency.json')) self.graph = network.CandidateGraph.from_adjacency_file(get_path('adjacency.json')) def test_get_name(self): node_number = self.graph.node_name_map['AS15-M-0297_SML.png'] name = self.graph.get_name(node_number) self.assertEquals(name, 'AS15-M-0297_SML.png') def test_add_image(self): with self.assertRaises(NotImplementedError): self.graph.add_image() self.assertEqual(self.graph.node_counter, 7) def test_adjacency_to_json(self): self.graph.adjacency_to_json('test_adjacency_to_json.json') self.assertTrue(os.path.exists('test_adjacency_to_json.json')) 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')) def test_extract_features(self): # also tests get_geodataset() and get_keypoints self.graph.extract_features(10) node_number = self.graph.node_name_map['AS15-M-0297_SML.png'] node = self.graph.node[node_number] self.assertEquals(len(node['image']), 1012) self.assertEquals(len(node['keypoints']), 10) self.assertEquals(len(node['descriptors']), 10) self.assertIsInstance(node['keypoints'][0], type(cv2.KeyPoint())) self.assertIsInstance(node['descriptors'][0], np.ndarray) self.assertEquals(self.graph.get_keypoints(node_number), node['keypoints']) def tearDown(self): try: os.remove('test_adjacency_to_json.json') os.remove('test_graph_to_json.json') except: pass
autocnet/matcher/matcher.py +100 −0 Original line number Diff line number Diff line Loading @@ -169,3 +169,103 @@ class FlannMatcher(object): 'destination_image', 'destination_idx', 'distance']) class OutlierDetector(object): """ A class which contains several outlier detection methods which all return True/False masks as pandas data series, which can be used as masks for the "matches" pandas dataframe which stores match information for each edge of the graph. Attributes ---------- """ def __init__(self): pass # (query only takes care of literal self-matches on a keypoint basis, not self-matches for the whole image) def self_neighbors(self, matches): """ Returns a pandas data series intended to be used as a mask. Each row is True if it is not matched to a point in the same image (good) and False if it is (bad.) Parameters ---------- matches : dataframe the matches dataframe stored along the edge of the graph containing matched points with columns containing: matched image name, query index, train index, and descriptor distance Returns ------- : dataseries Intended to mask the matches dataframe. True means the row is not matched to a point in the same image and false the row is. """ return matches.source_image != matches.destination_image def distance_ratio(self, matches, ratio=0.8): """ Compute and return a mask for the matches dataframe stored on each edge of the graph using the ratio test and distance_ratio set during initialization. Parameters ---------- matches : dataframe the matches dataframe stored along the edge of the graph containing matched points with columns containing: matched image name, query index, train index, and descriptor distance. ***Will only work as expected if matches already has dropped duplicates*** ratio: float the ratio between the first and second-best match distances for each keypoint to use as a bound for marking the first keypoint as "good." Returns ------- : dataseries Intended to mask the matches dataframe. Rows are True if the associated keypoint passes the ratio test and false otherwise. Keypoints without more than one match are True by default, since the ratio test will not work for them. """ #0.8 is Lowe's paper value -- can be changed. mask = [] temp_matches = matches.drop_duplicates() #don't want to deal with duplicates... for key, group in temp_matches.groupby('source_idx'): #won't work if there's only 1 match for each queryIdx if len(group) < 2: mask.append(True) else: if group['distance'].iloc[0] < ratio * group['distance'].iloc[1]: #this means distance _0_ is good and can drop all other distances mask.append(True) for i in range(len(group['distance']-1)): mask.append(False) else: for i in range(len(group['distance'])): mask.append(False) return pd.Series(mask) def mirroring_test(self, matches): """ Compute and return a mask for the matches dataframe on each edge of the graph which will keep only entries in which there is both a source -> destination match and a destination -> source match. Parameters ---------- matches : dataframe the matches dataframe stored along the edge of the graph containing matched points with columns containing: matched image name, query index, train index, and descriptor distance Returns ------- : dataseries Intended to mask the matches dataframe. Rows are True if the associated keypoint passes the mirroring test and false otherwise. That is, if 1->2, 2->1, both rows will be True, otherwise, they will be false. Keypoints with only one match will be False. Removes duplicate rows. """ return matches.duplicated(keep='first')
