def InstSegm(extent, boundary, t_ext=0.4, t_bound=0.2):
"""
INPUTS:
extent : extent prediction
boundary : boundary prediction
t_ext : threshold for extent
t_bound : threshold for boundary
OUTPUT:
instances
"""
# Threshold extent mask
ext_binary = np.uint8(extent >= t_ext)
# Artificially create strong boundaries for
# pixels with non-field labels
input_hws = np.copy(boundary)
input_hws[ext_binary == 0] = 1
# Create the directed graph
size = input_hws.shape[:2]
graph = hg.get_8_adjacency_graph(size)
edge_weights = hg.weight_graph(graph, input_hws, hg.WeightFunction.mean)
tree, altitudes = hg.watershed_hierarchy_by_dynamics(graph, edge_weights)
# Get individual fields
# by cutting the graph using altitude
instances = hg.labelisation_horizontal_cut_from_threshold(
tree, altitudes, threshold=t_bound).astype(np.float)
instances[ext_binary == 0] = np.nan
return instances
def test_labelisation_horizontal_cut(self):
tree = hg.Tree(np.asarray((5, 5, 6, 6, 6, 7, 7, 7)))
altitudes = np.asarray((0, 0, 0, 0, 0, 0.5, 0, 0.7), dtype=np.double)
ref_t0 = np.asarray((1, 2, 3, 3, 3), dtype=np.int32)
ref_t1 = np.asarray((1, 1, 2, 2, 2), dtype=np.int32)
ref_t2 = np.asarray((1, 1, 1, 1, 1), dtype=np.int32)
output_t0 = hg.labelisation_horizontal_cut_from_threshold(tree, altitudes, 0)
output_t1 = hg.labelisation_horizontal_cut_from_threshold(tree, altitudes, 0.5)
output_t2 = hg.labelisation_horizontal_cut_from_threshold(tree, altitudes, 0.7)
self.assertTrue(hg.is_in_bijection(ref_t0, output_t0))
self.assertTrue(hg.is_in_bijection(ref_t1, output_t1))
self.assertTrue(hg.is_in_bijection(ref_t2, output_t2))
def test_hierarchy_to_optimal_MumfordShah_energy_cut_hierarchy(self):
# Test strategy:
# 1) start from a random hierarchy
# 2) construct the corresponding optimal Mumford-Shah energy cut hierarchy
# 3) verify that the horizontal cuts of the new hierarchy corresponds to the
# optimal energy cuts of the first hierarchy obtained from the explicit MF energy
# and the function labelisation_optimal_cut_from_energy
shape = (10, 10)
g = hg.get_4_adjacency_graph(shape)
np.random.seed(2)
vertex_weights = np.random.rand(*shape)
edge_weights = hg.weight_graph(g, vertex_weights, hg.WeightFunction.L1)
tree1, altitudes1 = hg.watershed_hierarchy_by_area(g, edge_weights)
tree, altitudes = hg.hierarchy_to_optimal_MumfordShah_energy_cut_hierarchy(
tree1,
vertex_weights,
approximation_piecewise_linear_function=999999)
for a in altitudes:
if a != 0:
res = False
cut1 = hg.labelisation_horizontal_cut_from_threshold(
tree, altitudes, a)
# du to numerical issues, and especially as we test critical scale level lambda,
# we test several very close scale levels
for margin in [-1e-8, 0, 1e-8]:
mfs_energy = hg.attribute_piecewise_constant_Mumford_Shah_energy(
tree1, vertex_weights, a + margin)
cut2 = hg.labelisation_optimal_cut_from_energy(
tree1, mfs_energy)
res = res or hg.is_in_bijection(cut1, cut2)
self.assertTrue(res)
def get_cut_thr(tree, altitudes, thr=0.5):
labels = hg.labelisation_horizontal_cut_from_threshold(
tree, 1 - altitudes, 1 - thr)
return labels