def build_correspondance(self, visible_markers, camera_calibration,
min_marker_perimeter, min_id_confidence):
"""
- use all visible markers
- fit a convex quadrangle around it
- use quadrangle verts to establish perpective transform
- map all markers into surface space
- build up list of found markers and their uv coords
"""
all_verts = [
m['verts'] for m in visible_markers
if m['perimeter'] >= min_marker_perimeter
]
if not all_verts:
return
all_verts = np.array(all_verts, dtype=np.float32)
all_verts.shape = (
-1, 1, 2) # [vert,vert,vert,vert,vert...] with vert = [[r,c]]
# all_verts_undistorted_normalized centered in img center flipped in y and range [-1,1]
all_verts_undistorted_normalized = cv2.undistortPoints(
all_verts, np.asarray(camera_calibration['camera_matrix']),
np.asarray(camera_calibration['dist_coefs']) * self.use_distortion)
hull = cv2.convexHull(all_verts_undistorted_normalized,
clockwise=False)
#simplify until we have excatly 4 verts
if hull.shape[0] > 4:
new_hull = cv2.approxPolyDP(hull, epsilon=1, closed=True)
if new_hull.shape[0] >= 4:
hull = new_hull
if hull.shape[0] > 4:
curvature = abs(GetAnglesPolyline(hull, closed=True))
most_acute_4_threshold = sorted(curvature)[3]
hull = hull[curvature <= most_acute_4_threshold]
# all_verts_undistorted_normalized space is flipped in y.
# we need to change the order of the hull vertecies
hull = hull[[1, 0, 3, 2], :, :]
# now we need to roll the hull verts until we have the right orientation:
# all_verts_undistorted_normalized space has its origin at the image center.
# adding 1 to the coordinates puts the origin at the top left.
distance_to_top_left = np.sqrt((hull[:, :, 0] + 1)**2 +
(hull[:, :, 1] + 1)**2)
bot_left_idx = np.argmin(distance_to_top_left) + 1
hull = np.roll(hull, -bot_left_idx, axis=0)
#based on these 4 verts we calculate the transformations into a 0,0 1,1 square space
m_from_undistored_norm_space = m_verts_from_screen(hull)
self.detected = True
# map the markers vertices into the surface space (one can think of these as texture coordinates u,v)
marker_uv_coords = cv2.perspectiveTransform(
all_verts_undistorted_normalized, m_from_undistored_norm_space)
marker_uv_coords.shape = (
-1, 4, 1, 2) #[marker,marker...] marker = [ [[r,c]],[[r,c]] ]
# build up a dict of discovered markers. Each with a history of uv coordinates
for m, uv in zip(visible_markers, marker_uv_coords):
try:
self.markers[m['id']].add_uv_coords(uv)
except KeyError:
self.markers[m['id']] = Support_Marker(m['id'])
self.markers[m['id']].add_uv_coords(uv)
#average collection of uv correspondences accros detected markers
self.build_up_status = sum(
[len(m.collected_uv_coords)
for m in self.markers.values()]) / float(len(self.markers))
if self.build_up_status >= self.required_build_up:
self.finalize_correnspondance()
def build_correspondance(self, visible_markers):
"""
- use all visible markers
- fit a convex quadrangle around it
- use quadrangle verts to establish perpective transform
- map all markers into surface space
- build up list of found markers and their uv coords
"""
if visible_markers == []:
self.m_to_screen = None
self.m_from_screen = None
self.detected = False
return
all_verts = np.array([[m['verts_norm'] for m in visible_markers]])
all_verts.shape = (
-1, 1, 2) # [vert,vert,vert,vert,vert...] with vert = [[r,c]]
hull = cv2.convexHull(all_verts, clockwise=False)
#simplify until we have excatly 4 verts
if hull.shape[0] > 4:
new_hull = cv2.approxPolyDP(hull, epsilon=1, closed=True)
if new_hull.shape[0] >= 4:
hull = new_hull
if hull.shape[0] > 4:
curvature = abs(GetAnglesPolyline(hull, closed=True))
most_acute_4_threshold = sorted(curvature)[3]
hull = hull[curvature <= most_acute_4_threshold]
#now we need to roll the hull verts until we have the right orientation:
distance_to_origin = np.sqrt(hull[:, :, 0]**2 + hull[:, :, 1]**2)
top_left_idx = np.argmin(distance_to_origin)
hull = np.roll(hull, -top_left_idx, axis=0)
#based on these 4 verts we calculate the transformations into a 0,0 1,1 square space
self.m_to_screen = m_verts_to_screen(hull)
self.m_from_screen = m_verts_from_screen(hull)
self.detected = True
# map the markers vertices in to the surface space (one can think of these as texture coordinates u,v)
marker_uv_coords = cv2.perspectiveTransform(all_verts,
self.m_from_screen)
marker_uv_coords.shape = (
-1, 4, 1, 2) #[marker,marker...] marker = [ [[r,c]],[[r,c]] ]
# build up a dict of discovered markers. Each with a history of uv coordinates
for m, uv in zip(visible_markers, marker_uv_coords):
try:
self.markers[m['id']].add_uv_coords(uv)
except KeyError:
self.markers[m['id']] = Support_Marker(m['id'])
self.markers[m['id']].add_uv_coords(uv)
#average collection of uv correspondences accros detected markers
self.build_up_status = sum(
[len(m.collected_uv_coords)
for m in self.markers.values()]) / float(len(self.markers))
if self.build_up_status >= self.required_build_up:
self.finalize_correnspondance()
self.defined = True