def scenes2ares(seq_path, seq_name):
rgb_dir = os.path.join(seq_path, seq_name, 'rgb')
depth_dir = os.path.join(seq_path, seq_name, 'depth')
poses_dir = os.path.join(seq_path, seq_name, 'poses')
frames = sorted(glob.glob(os.path.join(rgb_dir, '*.jpg')))
frame_names = [seq.split('/')[-1].split('.jpg')[0] for seq in frames]
default_intrinsic = np.asarray([525, 525, 320, 240, 0, 0], dtype=np.float32)
frame_seq = FrameSeqData()
# Read the pose
for frame_idx, frame_name in enumerate(frame_names):
pose_file = os.path.join(poses_dir, frame_name + '.txt')
rgb_file = os.path.join(poses_dir, frame_name + '.jpg')
depth_file = os.path.join(poses_dir, frame_name + '.png')
# Read the pose
pose = np.loadtxt(pose_file).astype(np.float32).reshape(4, 4)
Tcw = cam_opt.camera_pose_inv(pose[:3, :3], pose[:3, 3])
timestamp = float(frame_idx)
frame_seq.append_frame(frame_idx=frame_idx,
img_file_name=os.path.join(seq_name, 'rgb', frame_name + '.jpg'),
Tcw=Tcw,
camera_intrinsic=default_intrinsic,
frame_dim=(480, 640),
time_stamp=timestamp,
depth_file_name=os.path.join(seq_name, 'depth', frame_name + '.png'))
return frame_seq
def read_tum_seq(tum_rgbd_base_dir, seq_name):
"""
Read the SUN3D sequence to the frames collection
:param sun3d_seq_dir: input sun3d sequence directory
:return: uniform frames collection.
"""
frames = FrameSeqData()
abs_seq_dir = os.path.join(tum_rgbd_base_dir, seq_name)
# Read intrinsic mat
fx = 525.0 # focal length x
fy = 525.0 # focal length y
cx = 319.5 # optical center x
cy = 239.5 # optical center y
K_param = np.asarray([fx, fy, cx, cy, 0.0, 0.0], dtype=np.float32)
default_img_dim = (480, 640)
if os.path.exists(os.path.join(abs_seq_dir, 'rdpose_associate.txt')):
gt_file = 'rdpose_associate.txt'
else:
gt_file = 'rd_associate.txt'
frame_idx = 0
with open(os.path.join(abs_seq_dir, gt_file), 'r') as f:
for line in f:
# Load frame data
if gt_file.startswith('rdpose_associate'):
timestamp, img_file_name, _, depth_file_name, _, tx, ty, tz, qx, qy, qz, qw = line.strip(
).split(' ')
tx = float(tx)
ty = float(ty)
tz = float(tz)
qx = float(qx)
qy = float(qy)
qz = float(qz)
qw = float(qw)
R_mat = trans.quaternion_matrix([qw, qx, qy,
qz]).astype(np.float32)
t = np.array([tx, ty, tz]).astype(np.float32)
Twc_mat = R_mat
Twc_mat[:3, 3] = t
Tcw = np.linalg.inv(Twc_mat)[:3, :]
else:
timestamp, img_file_name, _, depth_file_name = line.strip(
).split(' ')
Tcw = np.eye(4)[:3, :]
frames.append_frame(
frame_idx=frame_idx,
img_file_name=os.path.join(seq_name, img_file_name),
Tcw=Tcw[:3, :],
camera_intrinsic=K_param,
frame_dim=default_img_dim,
time_stamp=float(timestamp),
depth_file_name=os.path.join(seq_name, depth_file_name))
frame_idx += 1
return frames
def read_scannet_seq(scannet_base_dir, seq_name):
"""
Read SCANNET sequences to the frames collection
:param input_seq_dir: directory single SCANNET sequence.
:return: uniform frames collection.
"""
frames = FrameSeqData()
abs_seq_dir = os.path.join(scannet_base_dir, seq_name)
# Read camera intrinsic info.
intrinsic_txt = os.path.join(abs_seq_dir, 'info.txt')
if not os.path.exists(intrinsic_txt):
raise Exception("No camera intrinsic mat.")
with open(intrinsic_txt, "r") as intrinsic_file:
for line in intrinsic_file:
tokens = line.split(' = ')
if tokens[0].startswith("m_depthWidth"):
frame_w = int(tokens[1].strip())
elif tokens[0].startswith("m_depthHeight"):
frame_h = int(tokens[1].strip())
elif tokens[0].startswith("m_depthShift"):
shift_factor = float(tokens[1].strip())
if shift_factor != 1000:
raise Exception("Depth shift error")
elif tokens[0].startswith("m_calibrationDepthIntrinsic"):
k_tokens = tokens[1].split(' ')[:16]
K = np.asarray(k_tokens, dtype=np.float32).reshape(4, 4)
K_param = np.asarray(
[K[0, 0], K[1, 1], K[0, 2], K[1, 2], 0.0, 0.0],
dtype=np.float32)
samples_txt = os.path.join(abs_seq_dir, 'samples.txt')
if not os.path.exists(samples_txt):
raise Exception("No seq samples info.")
with open(samples_txt, "r") as sample_file:
for line in sample_file:
tokens = line.split(' ')
tokens[-1] = tokens[-1].strip()
frame_idx = int(tokens[0])
frame_name = tokens[1].split('/')[1].split('.')[0]
img_name = os.path.join(seq_name, 'rgb', frame_name + '.color.jpg')
depth_name = os.path.join(seq_name, 'depth',
frame_name + '.depth.png')
Twc = np.asarray(tokens[3:19], dtype=np.float32).reshape((4, 4))
Tcw = np.linalg.inv(Twc)[:3, :]
frames.append_frame(frame_idx,
img_name,
Tcw,
K_param, (frame_h, frame_w),
depth_file_name=depth_name)
return frames
def read_sun3d_seq(sun3d_base_dir, seq_name):
"""
Read the SUN3D sequence to the frames collection
:param sun3d_seq_dir: input sun3d sequence directory
:return: uniform frames collection.
"""
frames = FrameSeqData()
abs_seq_dir = os.path.join(sun3d_base_dir, seq_name)
# Read intrinsic mat
intrinsic_file_path = os.path.join(abs_seq_dir, 'intrinsics.txt')
if not os.path.exists(intrinsic_file_path):
raise Exception("DIR: %s ----" % abs_seq_dir)
K = np.loadtxt(intrinsic_file_path, dtype=np.float32).reshape((3, 3))
K_param = np.asarray([K[0, 0], K[1, 1], K[0, 2], K[1, 2], 0.0, 0.0], dtype=np.float32)
default_img_dim = (480, 640)
# Read extrinsic poses
ext_pose_file_path = sorted(glob.glob(os.path.join(abs_seq_dir, 'extrinsics', '*.txt')))[-1]
ext_poses = np.loadtxt(ext_pose_file_path)
n_frames = int(ext_poses.shape[0] / 3)
ext_poses = ext_poses.reshape((n_frames, 3, 4))
# Synchronize the image and depth with timestamp
depth_list = sorted(glob.glob(os.path.join(abs_seq_dir, 'depth', '*.png')))
depth_timestamps = []
for depth_path in depth_list:
depth_name = depth_path.split('/')[-1].strip()
depth_tokens = depth_name.split('-')[1].split('.')[0]
depth_timestamps.append(int(depth_tokens))
depth_timestamps = np.asarray(depth_timestamps)
img_list = sorted(glob.glob(os.path.join(abs_seq_dir, 'image', '*.jpg')))
assert len(img_list) == n_frames
for frame_idx, img_path in enumerate(img_list):
img_name = img_path.split('/')[-1].strip()
img_tokens = img_name.split('-')
frame_timestamp = int(img_tokens[1].split('.')[0])
# Find the closest depth frame
depth_frame_idx = np.argmin(np.abs(depth_timestamps - frame_timestamp))
depth_frame_path = depth_list[depth_frame_idx].split('/')[-1].strip()
Twc = ext_poses[frame_idx]
frames.append_frame(frame_idx=frame_idx,
img_file_name=os.path.join(seq_name, 'image', img_name),
Tcw=camera_pose_inv(Twc[:3, :3], Twc[:3, 3]),
camera_intrinsic=K_param,
frame_dim=default_img_dim,
time_stamp=float(frame_timestamp),
depth_file_name=os.path.join(seq_name, 'depth', depth_frame_path))
return frames
def scenes2ares(base_dir, seq_name):
rgb_dir = os.path.join(base_dir, seq_name, 'rgb')
depth_dir = os.path.join(base_dir, seq_name, 'depth')
poses_dir = os.path.join(base_dir, seq_name, 'poses')
frames = sorted(glob.glob(os.path.join(rgb_dir, '*.color.jpg')))
frame_names = [seq.split('/')[-1].split('.color.jpg')[0] for seq in frames]
default_intrinsic = np.asarray([572, 572, 320, 240, 0, 0],
dtype=np.float32)
default_rgb_intrinsic = np.asarray([1158.3, 1153.53, 649, 483.5, 0, 0],
dtype=np.float32)
frame_seq = FrameSeqData()
# Read the pose
frame_idx = 0
for i, frame_name in enumerate(frame_names):
pose_file = os.path.join(poses_dir, frame_name + '.pose.txt')
INF_flag = False
with open(pose_file, 'r') as f:
lines = f.readlines()
if 'INF' in lines[0]:
INF_flag = True
if INF_flag:
continue
# Read the pose
pose = np.loadtxt(pose_file).astype(np.float32).reshape(4, 4)
Tcw = cam_opt.camera_pose_inv(pose[:3, :3], pose[:3, 3])
timestamp = float(i)
frame_seq.append_frame(
frame_idx=frame_idx,
img_file_name=os.path.join(seq_name, 'rgb',
frame_name + '.color.jpg'),
Tcw=Tcw,
camera_intrinsic=default_intrinsic,
frame_dim=(480, 640),
time_stamp=timestamp,
depth_file_name=os.path.join(seq_name, 'depth',
frame_name + '.depth.png'),
rgb_intrinsic=default_rgb_intrinsic)
frame_idx += 1
return frame_seq