def load_masks(images):
"""
Return a list of boolean land masks.
Images must all be from the same station.
Arguments:
images (iterable): Image objects
"""
# All images must be from the same station (for now)
station = parse_image_path(images[0].path)['station']
pattern = re.compile(station + r'_[0-9]{8}_[0-9]{6}[^\/]*$')
is_station = [pattern.search(img.path) is not None for img in images[1:]]
assert all(is_station)
# Find all station svg with 'land' markup
imgsz = images[0].cam.imgsz
svg_paths = glob.glob(os.path.join(CG_PATH, 'svg', station + '_*.svg'))
markups = [glimpse.svg.parse_svg(path, imgsz=imgsz) for path in svg_paths]
land_index = np.where(['land' in markup for markup in markups])[0]
if len(land_index) == 0:
raise ValueError('No land masks found for station')
svg_paths = np.array(svg_paths)[land_index]
land_markups = np.array(markups)[land_index]
# Select svg files nearest to images, with preference within breaks
svg_datetimes = paths_to_datetimes(svg_paths)
svg_break_indices = np.array(
[_station_break_index(path) for path in svg_paths])
img_datetimes = [img.datetime for img in images]
distances = glimpse.helpers.pairwise_distance_datetimes(
img_datetimes, svg_datetimes)
nearest_index = []
for i, img in enumerate(images):
break_index = _station_break_index(img.path)
same_break = np.where(break_index == svg_break_indices)[0]
if same_break.size > 0:
i = same_break[np.argmin(distances[i][same_break])]
else:
raise ValueError('No mask found within motion breaks for image', i)
i = np.argmin(distances[i])
nearest_index.append(i)
nearest = np.unique(nearest_index)
# Make masks and expand per image without copying
masks = [None] * len(images)
image_sizes = np.array([img.cam.imgsz for img in images])
sizes = np.unique(image_sizes, axis=0)
for i in nearest:
polygons = land_markups[i]['land'].values()
is_nearest = nearest_index == i
for size in sizes:
scale = size / imgsz
rpolygons = [polygon * scale for polygon in polygons]
mask = glimpse.helpers.polygons_to_mask(rpolygons,
size=size).astype(np.uint8)
mask = sharedmem.copy(mask)
for j in np.where(is_nearest
& np.all(image_sizes == size, axis=1))[0]:
masks[j] = mask
return masks
def load_model(camera,
svgs=None,
keys=None,
step=None,
group_params=dict(),
station_calib=False,
camera_calib=False,
fixed=None):
# Gather motion control
motion_images, motion_controls, motion_cam_params = cg.camera_motion_matches(
camera, station_calib=station_calib, camera_calib=camera_calib)
# Gather svg control
svg_images, svg_controls, svg_cam_params = cg.camera_svg_controls(
camera,
keys=keys,
svgs=svgs,
correction=True,
station_calib=station_calib,
camera_calib=camera_calib,
step=step)
# Standardize image sizes
imgszs = np.unique([img.cam.imgsz for img in (motion_images + svg_images)],
axis=0)
if len(imgszs) > 1:
i_max = np.argmax(imgszs[:, 0])
print('Resizing images and controls to', imgszs[i_max])
for control in motion_controls + svg_controls:
control.resize(size=imgszs[i_max], force=True)
# Set new imgsz as original camera imgsz
for img in motion_images + svg_images:
img.cam.original_vector[6:8] = imgszs[i_max]
# Determine whether xyz can be optimized
stations = [cg.parse_image_path(img.path)['station'] for img in svg_images]
if fixed is None:
if len(stations) > 0 and (np.array(stations) == stations[0]).all():
fixed = cg.Stations()[stations[0]]['properties']['fixed']
else:
fixed = True
station = None if fixed else stations[0]
if station:
group_params = glimpse.helpers.merge_dicts(group_params,
dict(xyz=True))
model = glimpse.optimize.Cameras(
cams=[img.cam for img in motion_images + svg_images],
controls=motion_controls + svg_controls,
cam_params=motion_cam_params + svg_cam_params,
group_params=group_params)
return motion_images, svg_images, model, station
# not_small = np.diff(tranges, axis=1) >= min_dt
# tranges = tranges[not_small.ravel()]
# ranges = ranges[not_small.ravel()]
# Save results
station_iranges[station] = ranges
station_ranges[station] = tranges
station_images[station] = images
station_datetimes[station] = datetimes
# ---- Count dropped images ----
print('--- Image loss (after station filtering) ----')
for station in stations:
n = len(station_images[station])
x = np.arange(n)
nf = np.unique(np.concatenate([x[i:(j + 1)]
for i, j in station_iranges[station]])).size
dropped = n - nf
print(station, dropped, '(' + str(round(100 * dropped / n, 1)) + '%)')
# ---- Combine station ranges ----
# coverage, station_coverage
# Cut all ranges at all range endpoints
ranges = np.vstack([ranges for ranges in station_ranges.values()])
cuts = np.unique(ranges.ravel())
cut_ranges = glimpse.helpers.cut_ranges(ranges, cuts)
# Flatten to coverage
unique_cut_ranges = np.array(list({tuple(r) for r in cut_ranges}))
order = np.lexsort((unique_cut_ranges[:, 1], unique_cut_ranges[:, 0]))
coverage = unique_cut_ranges[order]
# Append stubs to coverage
print(station, services)
images = cg.load_images(station=station,
services=services,
snap=SNAP,
use_exif=False,
service_exif=True,
anchors=True,
viewdir=True,
viewdir_as_anchor=True)
# Keep only oriented images
images = np.array([img for img in images if img.anchor])
# Write animation(s)
# HACK: Split at camera changes to use observer.animate()
# HACK: Use k1 to quickly differentiate between cameras
ks = np.array([img.cam.k[0] for img in images])
for k in np.unique(ks):
idx = np.where(ks == k)[0]
sizes = np.row_stack([img.cam.imgsz for img in images[idx]])
unique_sizes = np.unique(sizes, axis=0)
if len(unique_sizes) > 1:
# Standardize image sizes
size = unique_sizes.min(axis=0)
not_size = np.any(sizes != size, axis=1)
f = images[~not_size][0].cam.f
for img in images[not_size]:
img.cam.resize(size, force=True)
# HACK: Fix focal length rounding errors
if any(img.cam.f - f > 0.1):
raise ValueError('Focal lengths cannot be reconciled')
img.cam.f = f
observer = glimpse.Observer(images[idx], cache=False).subset(snap=snap)
diagonal_neighbors = False # Whether to include diagonal neighbors
min_observers = 2 # Median ignores neighbors with observers below min if any above min
fill_missing = False # Whether to fill missing points with neighborhood median
nan_median = True # Whether to ignore missing values in computing median
exact_median_variance = False # Whether to use "exact" variance of median calculation (when averaging nearest neighbors)
# ---- Load medatada ----
# basenames: <date>.<interval id>
# template:
# ids: Unique point ids (flat index of points in template raster)
# Load tracks basenames
paths = glob.glob(os.path.join(tracks_path, '*.pkl'))
basepaths = [glimpse.helpers.strip_path(path) for path in paths]
basenames = np.unique([
re.sub(r"-[^-]+$", '', path) for path in basepaths
if re.search(r"[0-9]+-.+$", path) is not None
])
track_ids = [int(re.sub(r"^[0-9]+-", '', basename)) for basename in basenames]
# Load template
template = glimpse.Raster.read(os.path.join(points_path, 'template.tif'))
# Load ids of all tracked points
ids = []
for basename in basenames:
points = glimpse.helpers.read_pickle(
os.path.join(points_path, basename + '.pkl'))
ids = np.union1d(ids, points['ids']).astype(int)
# ---- Build arrays ----
# xyi: [ x | y | point_id ]
def camera_svg_controls(camera,
size=1,
force_size=False,
keys=None,
svgs=None,
correction=True,
step=None,
station_calib=False,
camera_calib=False,
synth=True):
"""
Return all SVG control objects available for a camera.
Arguments:
camera (str): Camera identifer
size: Image scale factor (number) or image size in pixels (nx, ny)
force_size (bool): Whether to force `size` even if different aspect ratio
than original size.
keys (iterable): SVG layers to include
svgs (iterable): SVG basenames to include
correction: Whether control objects should use elevation correction (bool)
or arguments to `glimpse.helpers.elevation_corrections()`
station_calib (bool): Whether to load station calibration. If `False`,
falls back to the station estimate.
camera_calib (bool): Whether to load camera calibrations. If `False`,
falls back to the EXIF estimate.
Returns:
list: Image objects
list: Control objects (Points, Lines)
list: Per-camera calibration parameters [{'viewdir': True}, ...]
"""
paths = glob.glob(os.path.join(CG_PATH, 'svg', '*.svg'))
if synth:
paths += glob.glob(os.path.join(CG_PATH, 'svg-synth', '*.pkl'))
paths += glob.glob(os.path.join(CG_PATH, 'svg-synth', '*.svg'))
basenames = np.unique([glimpse.helpers.strip_path(path) for path in paths])
images, controls, cam_params = [], [], []
for basename in basenames:
ids = parse_image_path(basename, sequence=True)
if ids['camera'] == camera:
calibration = load_calibrations(basename,
camera=camera_calib,
station=station_calib,
station_estimate=not station_calib,
merge=True)
img_path = find_image(basename)
img = glimpse.Image(img_path, cam=calibration)
control = []
if svgs is None or basename in svgs:
control += svg_controls(img,
keys=keys,
correction=correction,
step=step)
if synth:
control += synth_controls(img, step=None, directions=False)
if control:
for x in control:
x.resize(size, force=force_size)
images.append(img)
controls.extend(control)
cam_params.append(dict(viewdir=True))
return images, controls, cam_params
def load_images(station,
services,
use_exif=False,
service_exif=False,
anchors=False,
viewdir=True,
viewdir_as_anchor=False,
file_errors=True,
**kwargs):
"""
Return list of calibrated Image objects.
Any available station, camera, image, and viewdir calibrations are loaded
and images with image calibrations are marked as anchors.
Arguments:
station (str): Station identifier
services (iterable): Service identifiers
use_exif (bool): Whether to parse image datetimes from EXIF (slower)
rather than parsed from paths (faster)
service_exif (bool): Whether to extract EXIF from first image (faster)
or all images (slower) in service.
If `True`, `Image.datetime` is parsed from path.
Always `False` if `use_exif=True`.
anchors (bool): Whether to include anchor images even if
filtered out by `kwargs['snap']`
**kwargs: Arguments to `glimpse.helpers.select_datetimes()`
"""
if use_exif:
service_exif = False
# Sort services in time
if isinstance(services, str):
services = services,
services = np.sort(services)
# Parse datetimes of all candidate images
paths_service = [
glob.glob(
os.path.join(IMAGE_PATH, station, station + '_' + service,
'*.JPG')) for service in services
]
paths = np.hstack(paths_service)
basenames = [glimpse.helpers.strip_path(path) for path in paths]
if use_exif:
exifs = [glimpse.Exif(path) for path in paths]
datetimes = np.array([exif.datetime for exif in exifs])
else:
datetimes = paths_to_datetimes(basenames)
# Select images based on datetimes
indices = glimpse.helpers.select_datetimes(datetimes, **kwargs)
if anchors:
# Add anchors
# HACK: Ignore any <image>-<suffix>.json files
anchor_paths = glob.glob(
os.path.join(CG_PATH, 'images', station + '_*[0-9].json'))
anchor_basenames = [
glimpse.helpers.strip_path(path) for path in anchor_paths
]
if 'start' in kwargs or 'end' in kwargs:
# Filter by start, end
anchor_datetimes = np.asarray(paths_to_datetimes(anchor_basenames))
inrange = glimpse.helpers.select_datetimes(
anchor_datetimes,
**glimpse.helpers.merge_dicts(kwargs, dict(snap=None)))
anchor_basenames = np.asarray(anchor_basenames)[inrange]
anchor_indices = np.where(np.isin(basenames, anchor_basenames))[0]
indices = np.unique(np.hstack((indices, anchor_indices)))
service_breaks = np.hstack((0, np.cumsum([len(x) for x in paths_service])))
station_calibration = load_calibrations(station_estimate=station,
station=station,
merge=True,
file_errors=False)
images = []
for i, service in enumerate(services):
index = indices[(indices >= service_breaks[i])
& (indices < service_breaks[i + 1])]
if not index.size:
continue
service_calibration = glimpse.helpers.merge_dicts(
station_calibration,
load_calibrations(path=paths[index[0]],
camera=True,
merge=True,
file_errors=file_errors))
if service_exif:
exif = glimpse.Exif(paths[index[0]])
for j in index:
basename = basenames[j]
calibrations = load_calibrations(
image=basename,
viewdir=basename if viewdir else False,
station_estimate=station,
merge=False,
file_errors=False)
if calibrations['image']:
calibration = glimpse.helpers.merge_dicts(
service_calibration, calibrations['image'])
anchor = True
else:
calibration = glimpse.helpers.merge_dicts(
service_calibration,
dict(viewdir=calibrations['station_estimate']['viewdir']))
anchor = False
if viewdir and calibrations['viewdir']:
calibration = glimpse.helpers.merge_dicts(
calibration, calibrations['viewdir'])
if viewdir_as_anchor:
anchor = True
if use_exif:
exif = exifs[j]
elif not service_exif:
exif = None
if KEYPOINT_PATH:
keypoint_path = os.path.join(KEYPOINT_PATH, basename + '.pkl')
else:
keypoint_path = None
image = glimpse.Image(path=paths[j],
cam=calibration,
anchor=anchor,
exif=exif,
datetime=None if use_exif else datetimes[j],
keypoints_path=keypoint_path)
images.append(image)
return images