def add_point_constraints(ra, reconstruction_shots, reconstruction_name):
connections = connected_reconstructions(reconstruction_shots)
for connection in connections:
i1, (r1, g1) = load_reconstruction(connection[0].submodel_path,
connection[0].index)
i2, (r2, g2) = load_reconstruction(connection[1].submodel_path,
connection[1].index)
rec_name1 = reconstruction_name(connection[0])
rec_name2 = reconstruction_name(connection[1])
scale_treshold = 1.3
treshold_in_meter = 0.3
minimum_inliers = 20
status, T, inliers = reconstruction.resect_reconstruction(
r1, r2, g1, g2, treshold_in_meter, minimum_inliers)
if not status:
continue
s, R, t = multiview.decompose_similarity_transform(T)
if s > scale_treshold or s < (1.0/scale_treshold) or \
len(inliers) < minimum_inliers:
continue
for t1, t2 in inliers:
c1 = r1.points[t1].coordinates
c2 = r2.points[t2].coordinates
ra.add_common_point_constraint(rec_name1, c1[0], c1[1], c1[2],
rec_name2, c2[0], c2[1], c2[2],
1e-1)
def merge_two_reconstructions(r1, r2, config, threshold=1):
''' Merge two reconstructions with common tracks
'''
t1, t2 = r1['points'], r2['points']
common_tracks = list(set(t1) & set(t2))
# print 'Number of common tracks between two reconstructions: {0}'.format(len(common_tracks))
if len(common_tracks) > 6:
# Estimate similarity transform
p1 = np.array([t1[t]['coordinates'] for t in common_tracks])
p2 = np.array([t2[t]['coordinates'] for t in common_tracks])
T, inliers = multiview.fit_similarity_transform(p1,
p2,
max_iterations=1000,
threshold=threshold)
if len(inliers) >= 10:
s, A, b = multiview.decompose_similarity_transform(T)
r1p = r1
apply_similarity(r1p, s, A, b)
r = r2
r['shots'].update(r1p['shots'])
r['points'].update(r1p['points'])
align_reconstruction(r, config)
return [r]
else:
return [r1, r2]
else:
return [r1, r2]
def merge_two_reconstructions(r1, r2, config, threshold=1):
"""Merge two reconstructions with common tracks."""
t1, t2 = r1.points, r2.points
common_tracks = list(set(t1) & set(t2))
if len(common_tracks) > 6:
# Estimate similarity transform
p1 = np.array([t1[t].coordinates for t in common_tracks])
p2 = np.array([t2[t].coordinates for t in common_tracks])
T, inliers = multiview.fit_similarity_transform(p1,
p2,
max_iterations=1000,
threshold=threshold)
if len(inliers) >= 10:
s, A, b = multiview.decompose_similarity_transform(T)
r1p = r1
align.apply_similarity(r1p, s, A, b)
r = r2
r.shots.update(r1p.shots)
r.points.update(r1p.points)
align.align_reconstruction(r, None, config)
return [r]
else:
return [r1, r2]
else:
return [r1, r2]
def merge_two_reconstructions(r1, r2, config, threshold=1):
''' Merge two reconstructions with common tracks
'''
t1, t2 = r1.points, r2.points
common_tracks = list(set(t1) & set(t2))
# print 'Number of common tracks between two reconstructions: {0}'.format(len(common_tracks))
if len(common_tracks) > 6:
# Estimate similarity transform
p1 = np.array([t1[t].coordinates for t in common_tracks])
p2 = np.array([t2[t].coordinates for t in common_tracks])
T, inliers = multiview.fit_similarity_transform(p1, p2, max_iterations=1000, threshold=threshold)
if len(inliers) >= 10:
s, A, b = multiview.decompose_similarity_transform(T)
r1p = r1
apply_similarity(r1p, s, A, b)
r = r2
r.shots.update(r1p.shots)
r.points.update(r1p.points)
align_reconstruction(r, config)
return [r]
else:
return [r1, r2]
else:
return [r1, r2]
def add_point_constraints(ra, reconstruction_shots, reconstruction_name):
connections = connected_reconstructions(reconstruction_shots)
for connection in connections:
i1, (r1, g1) = load_reconstruction(
connection[0].submodel_path, connection[0].index)
i2, (r2, g2) = load_reconstruction(
connection[1].submodel_path, connection[1].index)
rec_name1 = reconstruction_name(connection[0])
rec_name2 = reconstruction_name(connection[1])
scale_treshold = 1.3
treshold_in_meter = 0.3
minimum_inliers = 20
status, T, inliers = reconstruction.resect_reconstruction(
r1, r2, g1, g2, treshold_in_meter, minimum_inliers)
if not status:
continue
s, R, t = multiview.decompose_similarity_transform(T)
if s > scale_treshold or s < (1.0/scale_treshold) or \
len(inliers) < minimum_inliers:
continue
for t1, t2 in inliers:
c1 = r1.points[t1].coordinates
c2 = r2.points[t2].coordinates
ra.add_common_point_constraint(
rec_name1, c1[0], c1[1], c1[2],
rec_name2, c2[0], c2[1], c2[2],
1e-1)
def merge_two_reconstructions(r1, r2, config, threshold=1):
"""Merge two reconstructions with common tracks IDs."""
common_tracks = list(set(r1.points) & set(r2.points))
worked, T, inliers = align_two_reconstruction(r1, r2, common_tracks, threshold)
if worked and len(inliers) >= 10:
s, A, b = multiview.decompose_similarity_transform(T)
r1p = r1
apply_similarity(r1p, s, A, b)
r = r2
r.shots.update(r1p.shots)
r.points.update(r1p.points)
align_reconstruction(r, None, config)
return [r]
else:
return [r1, r2]
def merge_two_reconstructions(r1, r2, config, threshold=1):
"""Merge two reconstructions with common tracks IDs."""
common_tracks = list(set(r1.points) & set(r2.points))
worked, T, inliers = align_two_reconstruction(
r1, r2, common_tracks, threshold)
if worked and len(inliers) >= 10:
s, A, b = multiview.decompose_similarity_transform(T)
r1p = r1
apply_similarity(r1p, s, A, b)
r = r2
r.shots.update(r1p.shots)
r.points.update(r1p.points)
align_reconstruction(r, None, config)
return [r]
else:
return [r1, r2]
def test_absolute_pose_generalized_shot():
"""Whole reconstruction resection (generalized pose) on a toy
reconstruction with 0.01 meter point noise and zero outliers."""
noise = 0.01
parameters = config.default_config()
scene, tracks = synthetic_reconstruction()
cluster1, cluster2 = split_synthetic_reconstruction(
scene, tracks, 3, noise)
cluster2, translation, scale = move_and_scale_cluster(cluster2)
status, T, inliers = reconstruction.\
resect_reconstruction(cluster1, cluster2,
tracks, tracks,
2*noise,
parameters['resection_min_inliers'])
assert status is True
s, A, b = multiview.decompose_similarity_transform(T)
np.testing.assert_almost_equal(scale, s, 2)
np.testing.assert_almost_equal(np.eye(3), A, 2)
np.testing.assert_almost_equal(translation, b, 2)
