EasyMocap/apps/calibration/read_colmap.py

# 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 cv2

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 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 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(
                id=image_id, qvec=qvec, tvec=tvec,
                camera_id=camera_id, name=image_name,
                xys=xys, point3D_ids=point3D_ids)
    return images


def read_points3D_text(path):
    """
    see: src/base/reconstruction.cc
        void Reconstruction::ReadPoints3DText(const std::string& path)
        void Reconstruction::WritePoints3DText(const std::string& path)
    """
    points3D = {}
    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()
                point3D_id = int(elems[0])
                xyz = np.array(tuple(map(float, elems[1:4])))
                rgb = np.array(tuple(map(int, elems[4:7])))
                error = float(elems[7])
                image_ids = np.array(tuple(map(int, elems[8::2])))
                point2D_idxs = np.array(tuple(map(int, elems[9::2])))
                points3D[point3D_id] = Point3D(id=point3D_id, xyz=xyz, rgb=rgb,
                                               error=error, image_ids=image_ids,
                                               point2D_idxs=point2D_idxs)
    return points3D


def read_points3d_binary(path_to_model_file):
    """
    see: src/base/reconstruction.cc
        void Reconstruction::ReadPoints3DBinary(const std::string& path)
        void Reconstruction::WritePoints3DBinary(const std::string& path)
    """
    points3D = {}
    with open(path_to_model_file, "rb") as fid:
        num_points = read_next_bytes(fid, 8, "Q")[0]
        for point_line_index in range(num_points):
            binary_point_line_properties = read_next_bytes(
                fid, num_bytes=43, format_char_sequence="QdddBBBd")
            point3D_id = binary_point_line_properties[0]
            xyz = np.array(binary_point_line_properties[1:4])
            rgb = np.array(binary_point_line_properties[4:7])
            error = np.array(binary_point_line_properties[7])
            track_length = read_next_bytes(
                fid, num_bytes=8, format_char_sequence="Q")[0]
            track_elems = read_next_bytes(
                fid, num_bytes=8*track_length,
                format_char_sequence="ii"*track_length)
            image_ids = np.array(tuple(map(int, track_elems[0::2])))
            point2D_idxs = np.array(tuple(map(int, track_elems[1::2])))
            points3D[point3D_id] = Point3D(
                id=point3D_id, xyz=xyz, rgb=rgb,
                error=error, image_ids=image_ids,
                point2D_idxs=point2D_idxs)
    return points3D


def read_model(path, ext):
    if ext == ".txt":
        cameras = read_cameras_text(os.path.join(path, "cameras" + ext))
        images = read_images_text(os.path.join(path, "images" + ext))
        points3D = read_points3D_text(os.path.join(path, "points3D") + ext)
    else:
        cameras = read_cameras_binary(os.path.join(path, "cameras" + ext))
        images = read_images_binary(os.path.join(path, "images" + ext))
        points3D = read_points3d_binary(os.path.join(path, "points3D") + ext)
    return cameras, images, points3D


def qvec2rotmat(qvec):
    return np.array([
        [1 - 2 * qvec[2]**2 - 2 * qvec[3]**2,
         2 * qvec[1] * qvec[2] - 2 * qvec[0] * qvec[3],
         2 * qvec[3] * qvec[1] + 2 * qvec[0] * qvec[2]],
        [2 * qvec[1] * qvec[2] + 2 * qvec[0] * qvec[3],
         1 - 2 * qvec[1]**2 - 2 * qvec[3]**2,
         2 * qvec[2] * qvec[3] - 2 * qvec[0] * qvec[1]],
        [2 * qvec[3] * qvec[1] - 2 * qvec[0] * qvec[2],
         2 * qvec[2] * qvec[3] + 2 * qvec[0] * qvec[1],
         1 - 2 * qvec[1]**2 - 2 * qvec[2]**2]])


def rotmat2qvec(R):
    Rxx, Ryx, Rzx, Rxy, Ryy, Rzy, Rxz, Ryz, Rzz = R.flat
    K = np.array([
        [Rxx - Ryy - Rzz, 0, 0, 0],
        [Ryx + Rxy, Ryy - Rxx - Rzz, 0, 0],
        [Rzx + Rxz, Rzy + Ryz, Rzz - Rxx - Ryy, 0],
        [Ryz - Rzy, Rzx - Rxz, Rxy - Ryx, Rxx + Ryy + Rzz]]) / 3.0
    eigvals, eigvecs = np.linalg.eigh(K)
    qvec = eigvecs[[3, 0, 1, 2], np.argmax(eigvals)]
    if qvec[0] < 0:
        qvec *= -1
    return qvec


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 _, 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_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 be 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 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 write_images_binary(images, path_to_model_file):
    """
    see: src/base/reconstruction.cc
        void Reconstruction::ReadImagesBinary(const std::string& path)
        void Reconstruction::WriteImagesBinary(const std::string& path)
    """
    with open(path_to_model_file, "wb") as fid:
        write_next_bytes(fid, len(images), "Q")
        for _, img in images.items():
            write_next_bytes(fid, img.id, "i")
            write_next_bytes(fid, img.qvec.tolist(), "dddd")
            write_next_bytes(fid, img.tvec.tolist(), "ddd")
            write_next_bytes(fid, img.camera_id, "i")
            for char in img.name:
                write_next_bytes(fid, char.encode("utf-8"), "c")
            write_next_bytes(fid, b"\x00", "c")
            write_next_bytes(fid, len(img.point3D_ids), "Q")
            for xy, p3d_id in zip(img.xys, img.point3D_ids):
                write_next_bytes(fid, [*xy, p3d_id], "ddq")

def write_images_text(images, path):
    """
    see: src/base/reconstruction.cc
        void Reconstruction::ReadImagesText(const std::string& path)
        void Reconstruction::WriteImagesText(const std::string& path)
    """
    if len(images) == 0:
        mean_observations = 0
    else:
        mean_observations = sum((len(img.point3D_ids) for _, img in images.items()))/len(images)
    HEADER = '# Image list with two lines of data per image:\n'
    '#   IMAGE_ID, QW, QX, QY, QZ, TX, TY, TZ, CAMERA_ID, NAME\n'
    '#   POINTS2D[] as (X, Y, POINT3D_ID)\n'
    '# Number of images: {}, mean observations per image: {}\n'.format(len(images), mean_observations)

    with open(path, "w") as fid:
        fid.write(HEADER)
        for _, img in images.items():
            image_header = [img.id, *img.qvec, *img.tvec, img.camera_id, img.name]
            first_line = " ".join(map(str, image_header))
            fid.write(first_line + "\n")

            points_strings = []
            for xy, point3D_id in zip(img.xys, img.point3D_ids):
                points_strings.append(" ".join(map(str, [*xy, point3D_id])))
            fid.write(" ".join(points_strings) + "\n")

def write_points3D_text(points3D, path):
    """
    see: src/base/reconstruction.cc
        void Reconstruction::ReadPoints3DText(const std::string& path)
        void Reconstruction::WritePoints3DText(const std::string& path)
    """
    if len(points3D) == 0:
        mean_track_length = 0
    else:
        mean_track_length = sum((len(pt.image_ids) for _, pt in points3D.items()))/len(points3D)
    HEADER = '# 3D point list with one line of data per point:\n'
    '#   POINT3D_ID, X, Y, Z, R, G, B, ERROR, TRACK[] as (IMAGE_ID, POINT2D_IDX)\n'
    '# Number of points: {}, mean track length: {}\n'.format(len(points3D), mean_track_length)

    with open(path, "w") as fid:
        fid.write(HEADER)
        for _, pt in points3D.items():
            point_header = [pt.id, *pt.xyz, *pt.rgb, pt.error]
            fid.write(" ".join(map(str, point_header)) + " ")
            track_strings = []
            for image_id, point2D in zip(pt.image_ids, pt.point2D_idxs):
                track_strings.append(" ".join(map(str, [image_id, point2D])))
            fid.write(" ".join(track_strings) + "\n")


def write_points3d_binary(points3D, path_to_model_file):
    """
    see: src/base/reconstruction.cc
        void Reconstruction::ReadPoints3DBinary(const std::string& path)
        void Reconstruction::WritePoints3DBinary(const std::string& path)
    """
    with open(path_to_model_file, "wb") as fid:
        write_next_bytes(fid, len(points3D), "Q")
        for _, pt in points3D.items():
            write_next_bytes(fid, pt.id, "Q")
            write_next_bytes(fid, pt.xyz.tolist(), "ddd")
            write_next_bytes(fid, pt.rgb.tolist(), "BBB")
            write_next_bytes(fid, pt.error, "d")
            track_length = pt.image_ids.shape[0]
            write_next_bytes(fid, track_length, "Q")
            for image_id, point2D_id in zip(pt.image_ids, pt.point2D_idxs):
                write_next_bytes(fid, [image_id, point2D_id], "ii")


class FileStorage(object):
    def __init__(self, filename, isWrite=False):
        version = cv2.__version__
        self.version = int(version.split('.')[0])
        if isWrite:
            self.fs = cv2.FileStorage(filename, cv2.FILE_STORAGE_WRITE)
        else:
            self.fs = cv2.FileStorage(filename, cv2.FILE_STORAGE_READ)

    def __del__(self):
        cv2.FileStorage.release(self.fs)

    def write(self, key, value, dt='mat'):
        if dt == 'mat':
            cv2.FileStorage.write(self.fs, key, value)
        elif dt == 'list':
            if self.version == 4: # 4.4
                # self.fs.write(key, '[')
                # for elem in value:
                #     self.fs.write('none', elem)
                # self.fs.write('none', ']')
                # import ipdb; ipdb.set_trace()
                self.fs.startWriteStruct(key, cv2.FileNode_SEQ)
                for elem in value:
                    self.fs.write('', elem)
                self.fs.endWriteStruct()
            else: # 3.4
                self.fs.write(key, '[')
                for elem in value:
                    self.fs.write('none', elem)
                self.fs.write('none', ']')

def main():
    if len(sys.argv) != 3:
        print("Usage: python read_model.py path/to/model/folder [.txt,.bin]")
        return

    cameras, images, points3D = read_model(path=sys.argv[1], ext=sys.argv[2])
    import cv2
    cameras_out = {}
    for key in cameras.keys():
        p = cameras[key].params
        if cameras[key].model == 'SIMPLE_RADIAL':
            f, cx, cy, k = p
            K = np.array([f, 0, cx, 0, f, cy, 0, 0, 1]).reshape(3, 3)
            dist = np.array([[k, 0, 0, 0, 0]])
        elif cameras[key].model == 'PINHOLE':
            fx, fy, cx, cy = p
            K = np.array([fx, 0, cx, 0, fy, cy, 0, 0, 1]).reshape(3, 3)
            dist = np.array([[0, 0, 0, 0, 0]])
        else:
            K = np.array([[p[0], 0, p[2], 0, p[1], p[3], 0, 0, 1]]).reshape(3, 3)
            dist = np.array([[p[4], p[5], p[6], p[7], 0.]])
        cameras_out[key] = {'K': K, 'dist': dist}
    mapkey = {}
    cameras_new = {}
    for key, val in images.items():
        cam = cameras_out[val.camera_id].copy()
        t = val.tvec.reshape(3, 1)
        R = qvec2rotmat(val.qvec)
        cam['R'] = R
        cam['Rvec'] = cv2.Rodrigues(R)[0]
        cam['T'] = t
        # mapkey[val.name.split('.')[0]] = val.camera_id
        
        cameras_new[val.name.split('.')[0]] = cam
        # cameras_new[val.name.split('.')[0].split('/')[0]] = cam
    keys = sorted(list(cameras_new.keys()))
    cameras_new = {key:cameras_new[key] for key in keys}
    print("num_cameras: {}/{}".format(len(cameras), len(cameras_new)))
    print("num_images:", len(images))
    print("num_points3D:", len(points3D))
    if len(points3D) > 0:
        keys = list(points3D.keys())
        xyz = np.stack([points3D[k].xyz for k in keys])
        rgb = np.stack([points3D[k].rgb for k in keys])
        import open3d as o3d
        pcd = o3d.geometry.PointCloud()
        pcd.points = o3d.utility.Vector3dVector(xyz)
        pcd.colors = o3d.utility.Vector3dVector(rgb/255.)
        from os.path import join
        pcdname = join(sys.argv[1], 'sparse.ply')
        o3d.io.write_point_cloud(pcdname, pcd)
        if False:
            o3d.visualization.draw_geometries([pcd])
    from easymocap.mytools.camera_utils import write_camera
    write_camera(cameras_new, sys.argv[1])


if __name__ == "__main__":
    main()