Commit 530512dd authored by Clément Pinard's avatar Clément Pinard
Browse files

add c++ pcl tools

parent 25c74ad8
# Copyright (c) 2018, ETH Zurich and UNC Chapel Hill.
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
#
# * Neither the name of ETH Zurich and UNC Chapel Hill nor the names of
# its contributors may be used to endorse or promote products derived
# from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
# Author: Johannes L. Schoenberger (jsch-at-demuc-dot-de)
# This script is based on an original implementation by True Price.
import sys
import sqlite3
import numpy as np
IS_PYTHON3 = sys.version_info[0] >= 3
MAX_IMAGE_ID = 2**31 - 1
CREATE_CAMERAS_TABLE = """CREATE TABLE IF NOT EXISTS cameras (
camera_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
model INTEGER NOT NULL,
width INTEGER NOT NULL,
height INTEGER NOT NULL,
params BLOB,
prior_focal_length INTEGER NOT NULL)"""
CREATE_DESCRIPTORS_TABLE = """CREATE TABLE IF NOT EXISTS descriptors (
image_id INTEGER PRIMARY KEY NOT NULL,
rows INTEGER NOT NULL,
cols INTEGER NOT NULL,
data BLOB,
FOREIGN KEY(image_id) REFERENCES images(image_id) ON DELETE CASCADE)"""
CREATE_IMAGES_TABLE = """CREATE TABLE IF NOT EXISTS images (
image_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
name TEXT NOT NULL UNIQUE,
camera_id INTEGER NOT NULL,
prior_qw REAL,
prior_qx REAL,
prior_qy REAL,
prior_qz REAL,
prior_tx REAL,
prior_ty REAL,
prior_tz REAL,
CONSTRAINT image_id_check CHECK(image_id >= 0 and image_id < {}),
FOREIGN KEY(camera_id) REFERENCES cameras(camera_id))
""".format(MAX_IMAGE_ID)
CREATE_TWO_VIEW_GEOMETRIES_TABLE = """
CREATE TABLE IF NOT EXISTS two_view_geometries (
pair_id INTEGER PRIMARY KEY NOT NULL,
rows INTEGER NOT NULL,
cols INTEGER NOT NULL,
data BLOB,
config INTEGER NOT NULL,
F BLOB,
E BLOB,
H BLOB)
"""
CREATE_KEYPOINTS_TABLE = """CREATE TABLE IF NOT EXISTS keypoints (
image_id INTEGER PRIMARY KEY NOT NULL,
rows INTEGER NOT NULL,
cols INTEGER NOT NULL,
data BLOB,
FOREIGN KEY(image_id) REFERENCES images(image_id) ON DELETE CASCADE)
"""
CREATE_MATCHES_TABLE = """CREATE TABLE IF NOT EXISTS matches (
pair_id INTEGER PRIMARY KEY NOT NULL,
rows INTEGER NOT NULL,
cols INTEGER NOT NULL,
data BLOB)"""
CREATE_NAME_INDEX = \
"CREATE UNIQUE INDEX IF NOT EXISTS index_name ON images(name)"
CREATE_ALL = "; ".join([
CREATE_CAMERAS_TABLE,
CREATE_IMAGES_TABLE,
CREATE_KEYPOINTS_TABLE,
CREATE_DESCRIPTORS_TABLE,
CREATE_MATCHES_TABLE,
CREATE_TWO_VIEW_GEOMETRIES_TABLE,
CREATE_NAME_INDEX
])
def image_ids_to_pair_id(image_id1, image_id2):
if image_id1 > image_id2:
image_id1, image_id2 = image_id2, image_id1
return image_id1 * MAX_IMAGE_ID + image_id2
def pair_id_to_image_ids(pair_id):
image_id2 = pair_id % MAX_IMAGE_ID
image_id1 = (pair_id - image_id2) / MAX_IMAGE_ID
return image_id1, image_id2
def array_to_blob(array):
if IS_PYTHON3:
return array.tostring()
else:
return np.getbuffer(array)
def blob_to_array(blob, dtype, shape=(-1,)):
if IS_PYTHON3:
return np.fromstring(blob, dtype=dtype).reshape(*shape)
else:
return np.frombuffer(blob, dtype=dtype).reshape(*shape)
class COLMAPDatabase(sqlite3.Connection):
@staticmethod
def connect(database_path):
return sqlite3.connect(database_path, factory=COLMAPDatabase)
def __init__(self, *args, **kwargs):
super(COLMAPDatabase, self).__init__(*args, **kwargs)
self.create_tables = lambda: self.executescript(CREATE_ALL)
self.create_cameras_table = \
lambda: self.executescript(CREATE_CAMERAS_TABLE)
self.create_descriptors_table = \
lambda: self.executescript(CREATE_DESCRIPTORS_TABLE)
self.create_images_table = \
lambda: self.executescript(CREATE_IMAGES_TABLE)
self.create_two_view_geometries_table = \
lambda: self.executescript(CREATE_TWO_VIEW_GEOMETRIES_TABLE)
self.create_keypoints_table = \
lambda: self.executescript(CREATE_KEYPOINTS_TABLE)
self.create_matches_table = \
lambda: self.executescript(CREATE_MATCHES_TABLE)
self.create_name_index = lambda: self.executescript(CREATE_NAME_INDEX)
def add_camera(self, model, width, height, params,
prior_focal_length=False, camera_id=None):
params = np.asarray(params, np.float64)
cursor = self.execute(
"INSERT INTO cameras VALUES (?, ?, ?, ?, ?, ?)",
(camera_id, model, width, height, array_to_blob(params),
prior_focal_length))
return cursor.lastrowid
def add_image(self, name, camera_id,
prior_q=np.full(4, np.NaN), prior_t=np.full(3, np.NaN), image_id=None):
cursor = self.execute(
"INSERT INTO images VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
(image_id, name, camera_id, prior_q[0], prior_q[1], prior_q[2],
prior_q[3], prior_t[0], prior_t[1], prior_t[2]))
return cursor.lastrowid
def add_keypoints(self, image_id, keypoints):
assert(len(keypoints.shape) == 2)
assert(keypoints.shape[1] in [2, 4, 6])
keypoints = np.asarray(keypoints, np.float32)
self.execute(
"INSERT INTO keypoints VALUES (?, ?, ?, ?)",
(image_id,) + keypoints.shape + (array_to_blob(keypoints),))
def add_descriptors(self, image_id, descriptors):
descriptors = np.ascontiguousarray(descriptors, np.uint8)
self.execute(
"INSERT INTO descriptors VALUES (?, ?, ?, ?)",
(image_id,) + descriptors.shape + (array_to_blob(descriptors),))
def add_matches(self, image_id1, image_id2, matches):
assert(len(matches.shape) == 2)
assert(matches.shape[1] == 2)
if image_id1 > image_id2:
matches = matches[:,::-1]
pair_id = image_ids_to_pair_id(image_id1, image_id2)
matches = np.asarray(matches, np.uint32)
self.execute(
"INSERT INTO matches VALUES (?, ?, ?, ?)",
(pair_id,) + matches.shape + (array_to_blob(matches),))
def add_two_view_geometry(self, image_id1, image_id2, matches,
F=np.eye(3), E=np.eye(3), H=np.eye(3), config=2):
assert(len(matches.shape) == 2)
assert(matches.shape[1] == 2)
if image_id1 > image_id2:
matches = matches[:,::-1]
pair_id = image_ids_to_pair_id(image_id1, image_id2)
matches = np.asarray(matches, np.uint32)
F = np.asarray(F, dtype=np.float64)
E = np.asarray(E, dtype=np.float64)
H = np.asarray(H, dtype=np.float64)
self.execute(
"INSERT INTO two_view_geometries VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
(pair_id,) + matches.shape + (array_to_blob(matches), config,
array_to_blob(F), array_to_blob(E), array_to_blob(H)))
def example_usage():
import os
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--database_path", default="database.db")
args = parser.parse_args()
if os.path.exists(args.database_path):
print("ERROR: database path already exists -- will not modify it.")
return
# Open the database.
db = COLMAPDatabase.connect(args.database_path)
# For convenience, try creating all the tables upfront.
db.create_tables()
# Create dummy cameras.
model1, width1, height1, params1 = \
0, 1024, 768, np.array((1024., 512., 384.))
model2, width2, height2, params2 = \
2, 1024, 768, np.array((1024., 512., 384., 0.1))
camera_id1 = db.add_camera(model1, width1, height1, params1)
camera_id2 = db.add_camera(model2, width2, height2, params2)
# Create dummy images.
image_id1 = db.add_image("image1.png", camera_id1)
image_id2 = db.add_image("image2.png", camera_id1)
image_id3 = db.add_image("image3.png", camera_id2)
image_id4 = db.add_image("image4.png", camera_id2)
# Create dummy keypoints.
#
# Note that COLMAP supports:
# - 2D keypoints: (x, y)
# - 4D keypoints: (x, y, theta, scale)
# - 6D affine keypoints: (x, y, a_11, a_12, a_21, a_22)
num_keypoints = 1000
keypoints1 = np.random.rand(num_keypoints, 2) * (width1, height1)
keypoints2 = np.random.rand(num_keypoints, 2) * (width1, height1)
keypoints3 = np.random.rand(num_keypoints, 2) * (width2, height2)
keypoints4 = np.random.rand(num_keypoints, 2) * (width2, height2)
db.add_keypoints(image_id1, keypoints1)
db.add_keypoints(image_id2, keypoints2)
db.add_keypoints(image_id3, keypoints3)
db.add_keypoints(image_id4, keypoints4)
# Create dummy matches.
M = 50
matches12 = np.random.randint(num_keypoints, size=(M, 2))
matches23 = np.random.randint(num_keypoints, size=(M, 2))
matches34 = np.random.randint(num_keypoints, size=(M, 2))
db.add_matches(image_id1, image_id2, matches12)
db.add_matches(image_id2, image_id3, matches23)
db.add_matches(image_id3, image_id4, matches34)
# Commit the data to the file.
db.commit()
# Read and check cameras.
rows = db.execute("SELECT * FROM cameras")
camera_id, model, width, height, params, prior = next(rows)
params = blob_to_array(params, np.float64)
assert camera_id == camera_id1
assert model == model1 and width == width1 and height == height1
assert np.allclose(params, params1)
camera_id, model, width, height, params, prior = next(rows)
params = blob_to_array(params, np.float64)
assert camera_id == camera_id2
assert model == model2 and width == width2 and height == height2
assert np.allclose(params, params2)
# Read and check keypoints.
keypoints = dict(
(image_id, blob_to_array(data, np.float32, (-1, 2)))
for image_id, data in db.execute(
"SELECT image_id, data FROM keypoints"))
assert np.allclose(keypoints[image_id1], keypoints1)
assert np.allclose(keypoints[image_id2], keypoints2)
assert np.allclose(keypoints[image_id3], keypoints3)
assert np.allclose(keypoints[image_id4], keypoints4)
# Read and check matches.
pair_ids = [image_ids_to_pair_id(*pair) for pair in
((image_id1, image_id2),
(image_id2, image_id3),
(image_id3, image_id4))]
matches = dict(
(pair_id_to_image_ids(pair_id),
blob_to_array(data, np.uint32, (-1, 2)))
for pair_id, data in db.execute("SELECT pair_id, data FROM matches")
)
assert np.all(matches[(image_id1, image_id2)] == matches12)
assert np.all(matches[(image_id2, image_id3)] == matches23)
assert np.all(matches[(image_id3, image_id4)] == matches34)
# Clean up.
db.close()
if os.path.exists(args.database_path):
os.remove(args.database_path)
if __name__ == "__main__":
example_usage()
# Copyright (c) 2018, ETH Zurich and UNC Chapel Hill.
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
#
# * Neither the name of ETH Zurich and UNC Chapel Hill nor the names of
# its contributors may be used to endorse or promote products derived
# from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
# Author: Johannes L. Schoenberger (jsch-at-demuc-dot-de)
import os
import sys
import collections
import numpy as np
import struct
import argparse
CameraModel = collections.namedtuple(
"CameraModel", ["model_id", "model_name", "num_params"])
Camera = collections.namedtuple(
"Camera", ["id", "model", "width", "height", "params"])
BaseImage = collections.namedtuple(
"Image", ["id", "qvec", "tvec", "camera_id", "name", "xys", "point3D_ids"])
Point3D = collections.namedtuple(
"Point3D", ["id", "xyz", "rgb", "error", "image_ids", "point2D_idxs"])
class Image(BaseImage):
def qvec2rotmat(self):
return qvec2rotmat(self.qvec)
CAMERA_MODELS = {
CameraModel(model_id=0, model_name="SIMPLE_PINHOLE", num_params=3),
CameraModel(model_id=1, model_name="PINHOLE", num_params=4),
CameraModel(model_id=2, model_name="SIMPLE_RADIAL", num_params=4),
CameraModel(model_id=3, model_name="RADIAL", num_params=5),
CameraModel(model_id=4, model_name="OPENCV", num_params=8),
CameraModel(model_id=5, model_name="OPENCV_FISHEYE", num_params=8),
CameraModel(model_id=6, model_name="FULL_OPENCV", num_params=12),
CameraModel(model_id=7, model_name="FOV", num_params=5),
CameraModel(model_id=8, model_name="SIMPLE_RADIAL_FISHEYE", num_params=4),
CameraModel(model_id=9, model_name="RADIAL_FISHEYE", num_params=5),
CameraModel(model_id=10, model_name="THIN_PRISM_FISHEYE", num_params=12)
}
CAMERA_MODEL_IDS = dict([(camera_model.model_id, camera_model)
for camera_model in CAMERA_MODELS])
CAMERA_MODEL_NAMES = dict([(camera_model.model_name, camera_model)
for camera_model in CAMERA_MODELS])
def read_next_bytes(fid, num_bytes, format_char_sequence, endian_character="<"):
"""Read and unpack the next bytes from a binary file.
:param fid:
:param num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc.
:param format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}.
:param endian_character: Any of {@, =, <, >, !}
:return: Tuple of read and unpacked values.
"""
data = fid.read(num_bytes)
return struct.unpack(endian_character + format_char_sequence, data)
def write_next_bytes(fid, data, format_char_sequence, endian_character="<"):
"""pack and write to a binary file.
:param fid:
:param data: data to send, if multiple elements are sent at the same time,
they should be encapsuled either in a list or a tuple
:param format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}.
should eb the same length as the data list or tuple
:param endian_character: Any of {@, =, <, >, !}
"""
if isinstance(data, (list, tuple)):
bytes = struct.pack(endian_character + format_char_sequence, *data)
else:
bytes = struct.pack(endian_character + format_char_sequence, data)
fid.write(bytes)
def read_cameras_text(path):
"""
see: src/base/reconstruction.cc
void Reconstruction::WriteCamerasText(const std::string& path)
void Reconstruction::ReadCamerasText(const std::string& path)
"""
cameras = {}
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
elems = line.split()
camera_id = int(elems[0])
model = elems[1]
width = int(elems[2])
height = int(elems[3])
params = np.array(tuple(map(float, elems[4:])))
cameras[camera_id] = Camera(id=camera_id, model=model,
width=width, height=height,
params=params)
return cameras
def read_cameras_binary(path_to_model_file):
"""
see: src/base/reconstruction.cc
void Reconstruction::WriteCamerasBinary(const std::string& path)
void Reconstruction::ReadCamerasBinary(const std::string& path)
"""
cameras = {}
with open(path_to_model_file, "rb") as fid:
num_cameras = read_next_bytes(fid, 8, "Q")[0]
for camera_line_index in range(num_cameras):
camera_properties = read_next_bytes(
fid, num_bytes=24, format_char_sequence="iiQQ")
camera_id = camera_properties[0]
model_id = camera_properties[1]
model_name = CAMERA_MODEL_IDS[camera_properties[1]].model_name
width = camera_properties[2]
height = camera_properties[3]
num_params = CAMERA_MODEL_IDS[model_id].num_params
params = read_next_bytes(fid, num_bytes=8*num_params,
format_char_sequence="d"*num_params)
cameras[camera_id] = Camera(id=camera_id,
model=model_name,
width=width,
height=height,
params=np.array(params))
assert len(cameras) == num_cameras
return cameras
def write_cameras_text(cameras, path):
"""
see: src/base/reconstruction.cc
void Reconstruction::WriteCamerasText(const std::string& path)
void Reconstruction::ReadCamerasText(const std::string& path)
"""
HEADER = '# Camera list with one line of data per camera:\n'
'# CAMERA_ID, MODEL, WIDTH, HEIGHT, PARAMS[]\n'
'# Number of cameras: {}\n'.format(len(cameras))
with open(path, "w") as fid:
fid.write(HEADER)
for id, cam in cameras.items():
to_write = [cam.id, cam.model, cam.width, cam.height, *cam.params]
line = " ".join([str(elem) for elem in to_write])
fid.write(line + "\n")
def write_cameras_binary(cameras, path_to_model_file):
"""
see: src/base/reconstruction.cc
void Reconstruction::WriteCamerasBinary(const std::string& path)
void Reconstruction::ReadCamerasBinary(const std::string& path)
"""
with open(path_to_model_file, "wb") as fid:
write_next_bytes(fid, len(cameras), "Q")
for _, cam in cameras.items():
model_id = CAMERA_MODEL_NAMES[cam.model].model_id
camera_properties = [cam.id,
model_id,
cam.width,
cam.height]
write_next_bytes(fid, camera_properties, "iiQQ")
for p in cam.params:
write_next_bytes(fid, float(p), "d")
return cameras
def read_images_text(path):
"""
see: src/base/reconstruction.cc
void Reconstruction::ReadImagesText(const std::string& path)
void Reconstruction::WriteImagesText(const std::string& path)
"""
images = {}
with open(path, "r") as fid:
while True:
line = fid.readline()
if not line:
break
line = line.strip()
if len(line) > 0 and line[0] != "#":
elems = line.split()
image_id = int(elems[0])
qvec = np.array(tuple(map(float, elems[1:5])))
tvec = np.array(tuple(map(float, elems[5:8])))
camera_id = int(elems[8])
image_name = elems[9]
elems = fid.readline().split()
xys = np.column_stack([tuple(map(float, elems[0::3])),
tuple(map(float, elems[1::3]))])
point3D_ids = np.array(tuple(map(int, elems[2::3])))
images[image_id] = Image(
id=image_id, qvec=qvec, tvec=tvec,
camera_id=camera_id, name=image_name,
xys=xys, point3D_ids=point3D_ids)
return images
def read_images_binary(path_to_model_file):
"""
see: src/base/reconstruction.cc
void Reconstruction::ReadImagesBinary(const std::string& path)
void Reconstruction::WriteImagesBinary(const std::string& path)
"""
images = {}
with open(path_to_model_file, "rb") as fid:
num_reg_images = read_next_bytes(fid, 8, "Q")[0]
for image_index in range(num_reg_images):
binary_image_properties = read_next_bytes(
fid, num_bytes=64, format_char_sequence="idddddddi")
image_id = binary_image_properties[0]
qvec = np.array(binary_image_properties[1:5])
tvec = np.array(binary_image_properties[5:8])
camera_id = binary_image_properties[8]
image_name = ""
current_char = read_next_bytes(fid, 1, "c")[0]
while current_char != b"\x00": # look for the ASCII 0 entry
image_name += current_char.decode("utf-8")
current_char = read_next_bytes(fid, 1, "c")[0]
num_points2D = read_next_bytes(fid, num_bytes=8,
format_char_sequence="Q")[0]
x_y_id_s = read_next_bytes(fid, num_bytes=24*num_points2D,
format_char_sequence="ddq"*num_points2D)
xys = np.column_stack([tuple(map(float, x_y_id_s[0::3])),
tuple(map(float, x_y_id_s[1::3]))])
point3D_ids = np.array(tuple(map(int, x_y_id_s[2::3])))
images[image_id] = Image(