def interpolate(x, t, t_int):
"""
Interpolate ground truth at the sensor timestamps
"""
# vector interpolation
x_int = np.zeros((t_int.shape[0], x.shape[1]))
for i in range(x.shape[1]):
if i in [4, 5, 6, 7]:
continue
x_int[:, i] = np.interp(t_int, t, x[:, i])
# quaternion interpolation
t_int = torch.Tensor(t_int - t[0])
t = torch.Tensor(t - t[0])
qs = SO3.qnorm(torch.Tensor(x[:, 4:8]))
x_int[:, 4:8] = SO3.qinterp(qs, t, t_int).numpy()
return x_int
def integrate_with_quaternions_superfast(self, N, raw_us, net_us):
imu_qs = SO3.qnorm(SO3.qexp(raw_us[:, :3].cuda().double()*self.dt))
net_qs = SO3.qnorm(SO3.qexp(net_us[:, :3].cuda().double()*self.dt))
Rot0 = SO3.qnorm(self.gt['qs'][:2].cuda().double())
imu_qs[0] = Rot0[0]
net_qs[0] = Rot0[0]
N = np.log2(imu_qs.shape[0])
for i in range(int(N)):
k = 2**i
imu_qs[k:] = SO3.qnorm(SO3.qmul(imu_qs[:-k], imu_qs[k:]))
net_qs[k:] = SO3.qnorm(SO3.qmul(net_qs[:-k], net_qs[k:]))
if int(N) < N:
k = 2**int(N)
k2 = imu_qs[k:].shape[0]
imu_qs[k:] = SO3.qnorm(SO3.qmul(imu_qs[:k2], imu_qs[k:]))
net_qs[k:] = SO3.qnorm(SO3.qmul(net_qs[:k2], net_qs[k:]))
imu_Rots = SO3.from_quaternion(imu_qs).float()
net_Rots = SO3.from_quaternion(net_qs).float()
return net_qs.cpu(), imu_Rots, net_Rots
def read_data(self, data_dir):
r"""Read the data from the dataset"""
f = os.path.join(self.predata_dir, 'dataset-room1_512_16_gt.p')
if True and os.path.exists(f):
return
print("Start read_data, be patient please")
def set_path(seq):
path_imu = os.path.join(data_dir, seq, "mav0", "imu0", "data.csv")
path_gt = os.path.join(data_dir, seq, "mav0", "mocap0", "data.csv")
return path_imu, path_gt
sequences = os.listdir(data_dir)
# read each sequence
for sequence in sequences:
print("\nSequence name: " + sequence)
if 'room' not in sequence:
continue
path_imu, path_gt = set_path(sequence)
imu = np.genfromtxt(path_imu, delimiter=",", skip_header=1)
gt = np.genfromtxt(path_gt, delimiter=",", skip_header=1)
# time synchronization between IMU and ground truth
t0 = np.max([gt[0, 0], imu[0, 0]])
t_end = np.min([gt[-1, 0], imu[-1, 0]])
# start index
idx0_imu = np.searchsorted(imu[:, 0], t0)
idx0_gt = np.searchsorted(gt[:, 0], t0)
# end index
idx_end_imu = np.searchsorted(imu[:, 0], t_end, 'right')
idx_end_gt = np.searchsorted(gt[:, 0], t_end, 'right')
# subsample
imu = imu[idx0_imu:idx_end_imu]
gt = gt[idx0_gt:idx_end_gt]
ts = imu[:, 0] / 1e9
# interpolate
t_gt = gt[:, 0] / 1e9
gt = self.interpolate(gt, t_gt, ts)
# take ground truth position
p_gt = gt[:, 1:4]
p_gt = p_gt - p_gt[0]
# take ground true quaternion pose
q_gt = SO3.qnorm(torch.Tensor(gt[:, 4:8]).double())
Rot_gt = SO3.from_quaternion(q_gt.cuda(), ordering='wxyz').cpu()
# convert from numpy
p_gt = torch.Tensor(p_gt).double()
v_gt = torch.zeros_like(p_gt).double()
v_gt[1:] = (p_gt[1:] - p_gt[:-1]) / self.dt
imu = torch.Tensor(imu[:, 1:]).double()
# compute pre-integration factors for all training
mtf = self.min_train_freq
dRot_ij = bmtm(Rot_gt[:-mtf], Rot_gt[mtf:])
dRot_ij = SO3.dnormalize(dRot_ij.cuda())
dxi_ij = SO3.log(dRot_ij).cpu()
# masks with 1 when ground truth is available, 0 otherwise
masks = dxi_ij.new_ones(dxi_ij.shape[0])
tmp = np.searchsorted(t_gt, ts[:-mtf])
diff_t = ts[:-mtf] - t_gt[tmp]
masks[np.abs(diff_t) > 0.01] = 0
# save all the sequence
mondict = {
'xs': torch.cat((dxi_ij, masks.unsqueeze(1)), 1).float(),
'us': imu.float(),
}
pdump(mondict, self.predata_dir, sequence + ".p")
# save ground truth
mondict = {
'ts': ts,
'qs': q_gt.float(),
'vs': v_gt.float(),
'ps': p_gt.float(),
}
pdump(mondict, self.predata_dir, sequence + "_gt.p")