def save_pseudo_vel(self, idx):
assert (idx < self.num_samples)
lidar_filename = os.path.join(self.lidar_dir, '%06d.bin' % (idx))
pseudolidar_filename = os.path.join(self.pseudo_lidar_dir,
'%06d.bin' % (idx))
save_filename = os.path.join(self.save_vel_pseudo_dir,
'%06d.bin' % (idx))
lidar_scan = utils.load_velo_scan(lidar_filename)
pseudolidar_scan = utils.load_velo_scan(pseudolidar_filename)
lidar_scan = np.concatenate((lidar_scan, pseudolidar_scan))
lidar_scan.tofile(save_filename)
def get_depth_pc(self, idx):
assert idx < self.num_samples
lidar_filename = os.path.join(self.depthpc_dir, "%06d.bin" % (idx))
is_exist = os.path.exists(lidar_filename)
if is_exist:
return utils.load_velo_scan(lidar_filename), is_exist
else:
return None, is_exist
def get_lidar(self, idx):
"""
:param idx:
:return:(n, 4), n point cloud, 4: x, y, z, reflectance values
"""
assert (idx < self.num_samples)
lidar_filename = os.path.join(self.lidar_dir, '%06d.bin' % (idx))
return utils.load_velo_scan(lidar_filename)
def __getitem__(self, item):
sample_idx = item
# sample = self.kitti_data.sample[sample_idx]
velo_pc = kitti_util.load_velo_scan(
os.path.join(self.data_path_pc,
sorted(os.listdir(self.data_path_pc))[item]))
# img are numpy array so transform must add ToPIL
img = kitti_util.load_image(
os.path.join(self.data_path_image,
sorted(os.listdir(self.data_path_image))[item]))
calibration_path = os.path.join(
self.data_path_calib,
sorted(os.listdir(self.data_path_calib))[item])
calibration = kitti_util.Calibration(calibration_path)
img = transform(img)
sample = {'image': img, 'velo_pc': velo_pc, 'calibration': calibration}
return sample
def get_lidar(self, idx):
assert idx < self.num_samples
lidar_filename = self.lidar_filenames[idx]
return utils.load_velo_scan(lidar_filename)
def get_lidar(self, idx):
assert(idx<self.num_samples)
lidar_filename = self.lidar_filenames[idx]
return utils.load_velo_scan(lidar_filename)
def get_lidar(self, idx):
assert(idx<self.num_samples)
lidar_filename = os.path.join(self.lidar_dir, '%06d.bin'%(idx))
return utils.load_velo_scan(lidar_filename)
def get_lidar(self, idx):
assert (idx < self.num_samples)
lidar_filename = os.path.join(self.lidar_dir, '%06d.bin' % (idx))
return utils.load_velo_scan(lidar_filename)
def get_lidar(self, idx):
lidar_filename = os.path.join(self.lidar_dir, '%06d.bin' % (idx))
lidar_scan = utils.load_velo_scan(lidar_filename)
return lidar_scan
def get_lidar(self, idx, drive_idx):
lidar_filename = os.path.join(self.lidar_dir, '%04d' % (drive_idx),
'%06d.bin' % (idx))
return utils.load_velo_scan(lidar_filename)
def get_lidar(self, idx):
assert (idx in self.lidar_filenames)
lidar_filename = self.lidar_filenames[idx]
return utils.load_velo_scan(lidar_filename)
def get_lidar(self, idx: str):
lidar_filename = os.path.join(self.lidar_dir, '{}.bin'.format(idx))
return utils.load_velo_scan(lidar_filename)
def get_lidar(self, idx, dtype=np.float32, n_vec=4):
idx = self.sample_ids[idx]
lidar_filename = os.path.join(self.lidar_dir, "%06d.bin" % (idx))
return utils.load_velo_scan(lidar_filename, dtype, n_vec)
def get_lidar(idx, dtype=np.float64, n_vec=4):
lidar_filename = path.join(lidar_dir, "%06d.bin" % (idx))
return utils.load_velo_scan(lidar_filename, dtype, n_vec)
def get_lidar(self, idx, dtype=np.float32, n_vec=4):
# assert idx < self.num_samples
lidar_filename = os.path.join(self.lidar_dir, f"{self.index_format}.bin" % (idx))
print(lidar_filename)
return utils.load_velo_scan(lidar_filename, dtype, n_vec)
def get_lidar(self, idx, dtype=np.float64, n_vec=4):
assert idx < self.num_samples
lidar_filename = os.path.join(self.lidar_dir, "%06d.bin" % (idx))
print(lidar_filename)
return utils.load_velo_scan(lidar_filename, dtype, n_vec)
def get_lidar(self, idx): #处理图片-H
assert(idx<self.num_samples) //断言，若不满足条件就报错-H
lidar_filename = os.path.join(self.lidar_dir, '%06d.bin'%(idx))
return utils.load_velo_scan(lidar_filename)
def load_frame_data(self,
data_idx_str,
random_flip=False,
random_rotate=False,
random_shift=False,
pca_jitter=False):
'''load one frame'''
if self.use_aug_scene:
data_idx = int(data_idx_str[2:])
else:
data_idx = int(data_idx_str)
# print(data_idx_str)
calib = self.kitti_dataset.get_calibration(data_idx) # 3 by 4 matrix
image = self.kitti_dataset.get_image(data_idx)
img_height, img_width = image.shape[0:2]
# data augmentation
if pca_jitter:
image = apply_pca_jitter(image)[0]
objects = []
if not self.use_aug_scene or data_idx_str[:2] == '00':
pc_velo = self.kitti_dataset.get_lidar(data_idx)
_, pc_image_coord, img_fov_inds = get_lidar_in_image_fov(
pc_velo[:, 0:3], calib, 0, 0, img_width, img_height, True)
pc_velo = pc_velo[img_fov_inds, :]
choice = np.random.choice(pc_velo.shape[0],
self.npoints,
replace=True)
point_set = pc_velo[choice, :]
pc_rect = np.zeros_like(point_set)
pc_rect[:, 0:3] = calib.project_velo_to_rect(point_set[:, 0:3])
pc_rect[:, 3] = point_set[:, 3]
if self.is_training:
objects = self.kitti_dataset.get_label_objects(data_idx)
else:
pc_rect = utils.load_velo_scan(
os.path.join(
self.kitti_path,
'aug_scene/rectified_data/{0}.bin'.format(data_idx_str)))
choice = np.random.choice(pc_rect.shape[0],
self.npoints,
replace=True)
pc_rect = pc_rect[choice, :]
if self.is_training:
objects = utils.read_label(
os.path.join(
self.kitti_path,
'aug_scene/aug_label/{0}.txt'.format(data_idx_str)))
objects = filter(
lambda obj: obj.type in self.types_list and obj.difficulty in self.
difficulties_list, objects)
gt_boxes = [] # ground truth boxes
#start = time.time()
seg_mask = np.zeros((pc_rect.shape[0]))
# data augmentation
if random_flip and np.random.random() > 0.5: # 50% chance flipping
pc_rect[:, 0] *= -1
for obj in objects:
obj.t = [-obj.t[0], obj.t[1], obj.t[2]]
# ensure that ry is [-pi, pi]
if obj.ry >= 0:
obj.ry = np.pi - obj.ry
else:
obj.ry = -np.pi - obj.ry
if random_rotate:
ry = (np.random.random() - 0.5) * math.radians(
20) # -10~10 degrees
pc_rect[:, 0:3] = rotate_points_along_y(pc_rect[:, 0:3], ry)
for obj in objects:
obj.t = rotate_points_along_y(obj.t, ry)
obj.ry -= ry
# ensure that ry is [-pi, pi]
if obj.ry > np.pi:
obj.ry -= 2 * np.pi
elif obj.ry < -np.pi:
obj.ry += 2 * np.pi
proposal_of_point = {} # point index to proposal vector
gt_box_of_point = {} # point index to corners_3d
for obj in objects:
_, obj_box_3d = utils.compute_box_3d(obj, calib.P)
_, obj_mask = extract_pc_in_box3d(pc_rect, obj_box_3d)
if np.sum(obj_mask) == 0:
# label without 3d points
# print('skip object without points')
continue
# IMPORTANT: this must match with NUM_SEG_CLASSES
#seg_mask[obj_mask] = g_type2onehotclass[obj.type]
seg_mask[obj_mask] = 1
gt_boxes.append(obj_box_3d)
obj_idxs = np.where(obj_mask)[0]
# data augmentation
# FIXME: jitter point will make valid loss growing
# Also may go out of image view
if random_shift and False: # jitter object points
pc_rect[obj_idxs, :3] = shift_point_cloud(
pc_rect[obj_idxs, :3], 0.02)
for idx in obj_idxs:
proposal_of_point[idx] = box_encoder.encode(
obj, pc_rect[idx, :3])
gt_box_of_point[idx] = obj_box_3d
# self.viz_frame(pc_rect, seg_mask, gt_boxes)
# return pc_rect, seg_mask, proposal_of_point, gt_box_of_point, gt_boxes
calib_matrix = np.copy(calib.P)
calib_matrix[0, :] *= (1200.0 / image.shape[1])
calib_matrix[1, :] *= (360.0 / image.shape[0])
#print('construct', time.time() - start)
return {
'pointcloud': pc_rect,
'image': cv2.resize(image, (1200, 360)),
'calib': calib_matrix,
'mask_label': seg_mask,
'proposal_of_point': self.get_proposal_out(proposal_of_point),
'gt_box_of_point': self.get_gt_box_of_points(gt_box_of_point),
'gt_boxes': gt_boxes,
'pc_choice': choice
}