def __call__(self, res, info):
res["mode"] = self.mode
if res["type"] in ["WaymoDataset"]:
if "combined" in res["lidar"]:
points = res["lidar"]["combined"]
else:
points = res["lidar"]["points"]
elif res["type"] in ["NuScenesDataset"]:
points = res["lidar"]["combined"]
else:
raise NotImplementedError
if self.mode == "train":
anno_dict = res["lidar"]["annotations"]
gt_dict = {
"gt_boxes": anno_dict["boxes"],
"gt_names": np.array(anno_dict["names"]).reshape(-1),
}
if self.mode == "train" and not self.no_augmentation:
selected = drop_arrays_by_name(
gt_dict["gt_names"], ["DontCare", "ignore", "UNKNOWN"]
)
_dict_select(gt_dict, selected)
if self.min_points_in_gt > 0:
point_counts = box_np_ops.points_count_rbbox(
points, gt_dict["gt_boxes"]
)
mask = point_counts >= min_points_in_gt
_dict_select(gt_dict, mask)
gt_boxes_mask = np.array(
[n in self.class_names for n in gt_dict["gt_names"]], dtype=np.bool_
)
if self.db_sampler:
sampled_dict = self.db_sampler.sample_all(
res["metadata"]["image_prefix"],
gt_dict["gt_boxes"],
gt_dict["gt_names"],
res["metadata"]["num_point_features"],
False,
gt_group_ids=None,
calib=None,
road_planes=None
)
if sampled_dict is not None:
sampled_gt_names = sampled_dict["gt_names"]
sampled_gt_boxes = sampled_dict["gt_boxes"]
sampled_points = sampled_dict["points"]
sampled_gt_masks = sampled_dict["gt_masks"]
gt_dict["gt_names"] = np.concatenate(
[gt_dict["gt_names"], sampled_gt_names], axis=0
)
gt_dict["gt_boxes"] = np.concatenate(
[gt_dict["gt_boxes"], sampled_gt_boxes]
)
gt_boxes_mask = np.concatenate(
[gt_boxes_mask, sampled_gt_masks], axis=0
)
points = np.concatenate([sampled_points, points], axis=0)
_dict_select(gt_dict, gt_boxes_mask)
gt_classes = np.array(
[self.class_names.index(n) + 1 for n in gt_dict["gt_names"]],
dtype=np.int32,
)
gt_dict["gt_classes"] = gt_classes
gt_dict["gt_boxes"], points = prep.random_flip_both(gt_dict["gt_boxes"], points)
gt_dict["gt_boxes"], points = prep.global_rotation(
gt_dict["gt_boxes"], points, rotation=self.global_rotation_noise
)
gt_dict["gt_boxes"], points = prep.global_scaling_v2(
gt_dict["gt_boxes"], points, *self.global_scaling_noise
)
gt_dict["gt_boxes"], points = prep.global_translate_(
gt_dict["gt_boxes"], points, noise_translate_std=self.global_translate_std
)
elif self.no_augmentation:
gt_boxes_mask = np.array(
[n in self.class_names for n in gt_dict["gt_names"]], dtype=np.bool_
)
_dict_select(gt_dict, gt_boxes_mask)
gt_classes = np.array(
[self.class_names.index(n) + 1 for n in gt_dict["gt_names"]],
dtype=np.int32,
)
gt_dict["gt_classes"] = gt_classes
if self.shuffle_points:
np.random.shuffle(points)
res["lidar"]["points"] = points
if self.mode == "train":
res["lidar"]["annotations"] = gt_dict
return res, info
def __call__(self, res, info):
# get points
res["mode"] = self.mode
if res["type"] in ["KittiDataset"]:
points = res["lidar"]["points"]
# get gt_boxes (x,y,z(velo), w, l, h, ry), gt_names and difficulty levels
if self.mode == "train":
anno_dict = res["lidar"]["annotations"]
gt_dict = {
"gt_boxes": anno_dict["boxes"],
"gt_names": np.array(anno_dict["names"]).reshape(-1),
}
if "difficulty" not in anno_dict: # True, todo: we may try to make it act.
difficulty = np.zeros([anno_dict["boxes"].shape[0]],
dtype=np.int32) # todo: all set as 0
gt_dict["difficulty"] = difficulty
else:
gt_dict["difficulty"] = anno_dict["difficulty"]
# get calib
calib = res["calib"] if "calib" in res else None
if self.mode == "train":
selected = kitti.drop_arrays_by_name(
gt_dict["gt_names"],
["DontCare", "ignore"
]) # todo: where is the definition of ignore???
_dict_select(gt_dict, selected)
# False
if self.remove_unknown:
remove_mask = gt_dict["difficulty"] == -1
gt_boxes_remove = gt_dict['gt_boxes'][remove_mask]
gt_boxes_remove[:, 3:6] += 0.25
masks = box_np_ops.points_in_rbbox(points, gt_boxes_remove)
points = points[np.logical_not(masks.any(-1))]
keep_mask = np.logical_not(remove_mask)
_dict_select(gt_dict, keep_mask)
# discard
gt_dict.pop("difficulty")
# False, todo: remove those gt_boxes with too little points
if self.min_points_in_gt > 0:
point_counts = box_np_ops.points_count_rbbox(
points, gt_dict["gt_boxes"])
mask = point_counts >= self.min_points_in_gt
_dict_select(gt_dict, mask)
# remove untargeted category objects; todo: what about the similar types
gt_boxes_mask = np.array(
[n in self.class_names for n in gt_dict["gt_names"]],
dtype=np.bool_)
# perform gt-augmentation
if self.db_sampler: # GT-AUG: filter_by_min_num_points, filter_by_difficulty
sampled_dict = self.db_sampler.sample_all(
res["metadata"]["image_prefix"],
gt_dict["gt_boxes"],
gt_dict["gt_names"],
res["metadata"]["num_point_features"],
self.random_crop, # False
gt_group_ids=None,
calib=calib,
targeted_class_names=self.class_names,
)
if sampled_dict is not None:
sampled_gt_names = sampled_dict["gt_names"]
sampled_gt_boxes = sampled_dict["gt_boxes"]
sampled_points = sampled_dict["points"]
sampled_gt_masks = sampled_dict["gt_masks"] # all 1.
gt_dict["gt_names"] = np.concatenate(
[gt_dict["gt_names"], sampled_gt_names], axis=0)
gt_dict["gt_boxes"] = np.concatenate(
[gt_dict["gt_boxes"], sampled_gt_boxes])
gt_boxes_mask = np.concatenate(
[gt_boxes_mask, sampled_gt_masks], axis=0)
# True, remove points in original scene with location occupied by auged gt boxes.
if self.remove_points_after_sample:
# points_in_rbbox is much faster than roipool3d.pts_in_boxes3d_velo_cpu
masks = box_np_ops.points_in_rbbox(
points, sampled_gt_boxes)
points = points[np.logical_not(masks.any(-1))]
points = np.concatenate(
[sampled_points, points], axis=0
) # concat existed points and points in gt-aug boxes
# per-object augmentation
prep.noise_per_object_v4_(
gt_dict["gt_boxes"], # x,y,z(lidar), w, l, h, ry(cam)
points,
gt_boxes_mask,
rotation_perturb=self.gt_rotation_noise, # rotation noise
center_noise_std=self.gt_loc_noise_std, # translation noise
global_random_rot_range=self.
global_random_rot_range, # no need here due to prep.global_rotation later.
group_ids=None,
num_try=100,
data_aug_with_context=self.data_aug_with_context,
data_aug_random_drop=self.data_aug_random_drop,
)
_dict_select(gt_dict,
gt_boxes_mask) # get gt_boxes of specific class
gt_classes = np.array(
[self.class_names.index(n) + 1 for n in gt_dict["gt_names"]],
dtype=np.int32,
)
gt_dict["gt_classes"] = gt_classes
# global augmentation
gt_dict["gt_boxes"], points = prep.random_flip(
gt_dict["gt_boxes"], points)
# gt_dict["gt_boxes"], points = prep.global_translate_(gt_dict["gt_boxes"], points, self.global_translate_noise_std)
gt_dict["gt_boxes"], points = prep.global_rotation(
gt_dict["gt_boxes"],
points,
rotation=self.global_rotation_noise)
gt_dict["gt_boxes"], points = prep.global_scaling_v2(
gt_dict["gt_boxes"], points, *self.global_scaling_noise)
if self.shuffle_points:
# shuffle is a little slow.
# np.random.shuffle(points)
choice = np.random.choice(np.arange(points.shape[0]),
points.shape[0],
replace=False)
points = points[choice]
# points sampling
if self.mode == "train" and self.random_select: # False
if self.npoints < points.shape[0]:
pts_depth = points[:,
2] # should be points[:, 0] (x-axis in velo coord) here
pts_near_flag = pts_depth < 40.0
far_idxs_choice = np.where(pts_near_flag == 0)[0]
near_idxs = np.where(pts_near_flag == 1)[0]
near_idxs_choice = np.random.choice(near_idxs,
self.npoints -
len(far_idxs_choice),
replace=False)
choice = (np.concatenate(
(near_idxs_choice, far_idxs_choice), axis=0)
if len(far_idxs_choice) > 0 else near_idxs_choice)
np.random.shuffle(choice)
else:
choice = np.arange(0, len(points), dtype=np.int32)
if self.npoints > len(points):
extra_choice = np.random.choice(choice,
self.npoints - len(points),
replace=False)
choice = np.concatenate((choice, extra_choice), axis=0)
np.random.shuffle(choice)
points = points[choice]
# False, uniformize intensity
if self.symmetry_intensity:
points[:, -1] -= 0.5 # translate intensity to [-0.5, 0.5]
# points[:, -1] *= 2
res["lidar"]["points"] = points
if self.mode == "train":
res["lidar"]["annotations"] = gt_dict
return res, info
def __call__(self, res, info):
# get points
res["mode"] = self.mode # train or val
if res["type"] in ["KittiDataset"]:
points = res["lidar"]["points"]
#import ipdb; ipdb.set_trace()
# get gt_boxes (x,y,z(velo), w, l, h, ry), class_names and difficulty levels
if self.mode == "train":
anno_dict = res["lidar"]["annotations"]
gt_dict = {
"gt_boxes": anno_dict["boxes"],
"gt_names": np.array(anno_dict["names"]).reshape(-1),
}
if "difficulty" not in anno_dict: # True
difficulty = np.zeros([anno_dict["boxes"].shape[0]],
dtype=np.int32) # todo: all set as 0
gt_dict["difficulty"] = difficulty
else:
gt_dict["difficulty"] = anno_dict["difficulty"]
# get calib
if "calib" in res:
calib = res["calib"]
else:
calib = None
'''
if self.add_rgb_to_points: # False
assert calib is not None and "image" in res
image_path = res["image"]["image_path"]
image = (imgio.imread(str(pathlib.Path(root_path) / image_path)).astype(np.float32) / 255)
points_rgb = box_np_ops.add_rgb_to_points(points, image, calib["rect"], calib["Trv2c"], calib["P2"])
points = np.concatenate([points, points_rgb], axis=1)
num_point_features += 3
if self.reference_detections is not None: # False
assert calib is not None and "image" in res
C, R, T = box_np_ops.projection_matrix_to_CRT_kitti(P2)
frustums = box_np_ops.get_frustum_v2(reference_detections, C)
frustums -= T
frustums = np.einsum("ij, akj->aki", np.linalg.inv(R), frustums)
frustums = box_np_ops.camera_to_lidar(frustums, rect, Trv2c)
surfaces = box_np_ops.corner_to_surfaces_3d_jit(frustums)
masks = points_in_convex_polygon_3d_jit(points, surfaces)
points = points[masks.any(-1)]
if self.remove_outside_points: # False, as points are loaded from reduced .bin file
assert calib is not None
image_shape = res["image"]["image_shape"]
points = box_np_ops.remove_outside_points(points, calib["rect"], calib["Trv2c"], calib["P2"], image_shape)
if self.remove_environment is True and self.mode == "train": # False
selected = kitti.keep_arrays_by_name(gt_names, target_assigner.classes)
_dict_select(gt_dict, selected)
masks = box_np_ops.points_in_rbbox(points, gt_dict["gt_boxes"])
points = points[masks.any(-1)]
'''
if self.mode == "train":
# redundant: discard dc and ignore gt
selected = kitti.drop_arrays_by_name(
gt_dict["gt_names"],
["DontCare", "ignore"
]) # todo: where is the definition of ignore???
_dict_select(gt_dict, selected)
# False, todo: remove those gt_boxes with difficulty as -1
if self.remove_unknown:
remove_mask = gt_dict["difficulty"] == -1
"""
gt_boxes_remove = gt_boxes[remove_mask]
gt_boxes_remove[:, 3:6] += 0.25
points = prep.remove_points_in_boxes(points, gt_boxes_remove)
"""
keep_mask = np.logical_not(remove_mask)
_dict_select(gt_dict, keep_mask)
# discard
gt_dict.pop("difficulty")
# False, todo: remove those gt_boxes with too little points
if self.min_points_in_gt > 0:
point_counts = box_np_ops.points_count_rbbox(
points, gt_dict["gt_boxes"])
mask = point_counts >= self.min_points_in_gt
_dict_select(gt_dict, mask)
# remove untargeted category objects; todo: mask re-implementation; 'car', what about the similar types
# if self.class_names.__len__() == 1:
# gt_boxes_mask = gt_dict["gt_names"] == self.class_names[0]
gt_boxes_mask = np.array(
[n in self.class_names for n in gt_dict["gt_names"]],
dtype=np.bool_)
# perform gt-augmentation
if self.db_sampler: # filter_by_min_num_points, filter_by_difficulty
sampled_dict = self.db_sampler.sample_all(
res["metadata"]["image_prefix"],
gt_dict["gt_boxes"],
gt_dict["gt_names"],
res["metadata"]["num_point_features"],
self.random_crop, # False
gt_group_ids=None,
calib=calib,
)
if sampled_dict is not None:
sampled_gt_names = sampled_dict["gt_names"]
sampled_gt_boxes = sampled_dict["gt_boxes"]
sampled_points = sampled_dict["points"]
sampled_gt_masks = sampled_dict["gt_masks"]
gt_dict["gt_names"] = np.concatenate(
[gt_dict["gt_names"], sampled_gt_names], axis=0)
gt_dict["gt_boxes"] = np.concatenate(
[gt_dict["gt_boxes"], sampled_gt_boxes])
gt_boxes_mask = np.concatenate(
[gt_boxes_mask, sampled_gt_masks], axis=0)
if self.remove_points_after_sample:
masks = box_np_ops.points_in_rbbox(
points, sampled_gt_boxes)
points = points[np.logical_not(masks.any(-1))]
points = np.concatenate(
[sampled_points, points], axis=0
) # concat existed points and points in gt-aug boxes
prep.noise_per_object_v3_(
gt_dict["gt_boxes"],
points,
gt_boxes_mask,
rotation_perturb=self.gt_rotation_noise,
center_noise_std=self.gt_loc_noise_std,
global_random_rot_range=self.global_random_rot_range,
group_ids=None,
num_try=100,
)
_dict_select(gt_dict,
gt_boxes_mask) # get gt_boxes of specific class
gt_classes = np.array(
[self.class_names.index(n) + 1 for n in gt_dict["gt_names"]],
dtype=np.int32,
)
gt_dict["gt_classes"] = gt_classes
# data augmentation here
gt_dict["gt_boxes"], points = prep.random_flip(
gt_dict["gt_boxes"], points)
gt_dict["gt_boxes"], points = prep.global_rotation(
gt_dict["gt_boxes"],
points,
rotation=self.global_rotation_noise)
gt_dict["gt_boxes"], points = prep.global_scaling_v2(
gt_dict["gt_boxes"], points, *self.global_scaling_noise)
if self.shuffle_points: # todo: not efficient, use choice
# shuffle is a little slow.
np.random.shuffle(points)
# points sampling
if self.mode == "train" and self.random_select: # False
if self.npoints < points.shape[0]:
pts_depth = points[:, 2]
pts_near_flag = pts_depth < 40.0
far_idxs_choice = np.where(pts_near_flag == 0)[0]
near_idxs = np.where(pts_near_flag == 1)[0]
near_idxs_choice = np.random.choice(near_idxs,
self.npoints -
len(far_idxs_choice),
replace=False)
choice = (np.concatenate(
(near_idxs_choice, far_idxs_choice), axis=0)
if len(far_idxs_choice) > 0 else near_idxs_choice)
np.random.shuffle(choice)
else:
choice = np.arange(0, len(points), dtype=np.int32)
if self.npoints > len(points):
extra_choice = np.random.choice(choice,
self.npoints - len(points),
replace=False)
choice = np.concatenate((choice, extra_choice), axis=0)
np.random.shuffle(choice)
points = points[choice]
# uniformize intensity
if self.symmetry_intensity:
points[:, -1] -= 0.5 # translate intensity to [-0.5, 0.5]
# points[:, -1] *= 2
res["lidar"]["points"] = points
if self.mode == "train":
res["lidar"]["annotations"] = gt_dict
return res, info
def __call__(self, res, info):
res["mode"] = self.mode
if res["type"] in ["KittiDataset", "WaymoDataset", "LyftDataset"]:
points = res["lidar"]["points"]
elif res["type"] in ["NuScenesDataset"]:
points = res["lidar"]["combined"]
if self.mode == "train":
anno_dict = res["lidar"]["annotations"]
gt_dict = {
"gt_boxes": anno_dict["boxes"],
"gt_names": np.array(anno_dict["names"]).reshape(-1),
}
if "difficulty" not in anno_dict:
difficulty = np.zeros([anno_dict["boxes"].shape[0]],
dtype=np.int32)
gt_dict["difficulty"] = difficulty
else:
gt_dict["difficulty"] = anno_dict["difficulty"]
if "calib" in res:
calib = res["calib"]
else:
calib = None
if self.add_rgb_to_points:
assert calib is not None and "image" in res
image_path = res["image"]["image_path"]
image = (imgio.imread(str(pathlib.Path(root_path) /
image_path)).astype(np.float32) / 255)
points_rgb = box_np_ops.add_rgb_to_points(points, image,
calib["rect"],
calib["Trv2c"],
calib["P2"])
points = np.concatenate([points, points_rgb], axis=1)
num_point_features += 3
if self.reference_detections is not None:
assert calib is not None and "image" in res
C, R, T = box_np_ops.projection_matrix_to_CRT_kitti(P2)
frustums = box_np_ops.get_frustum_v2(reference_detections, C)
frustums -= T
frustums = np.einsum("ij, akj->aki", np.linalg.inv(R), frustums)
frustums = box_np_ops.camera_to_lidar(frustums, rect, Trv2c)
surfaces = box_np_ops.corner_to_surfaces_3d_jit(frustums)
masks = points_in_convex_polygon_3d_jit(points, surfaces)
points = points[masks.any(-1)]
if self.remove_outside_points:
assert calib is not None
image_shape = res["metadata"]["image_shape"]
points = box_np_ops.remove_outside_points(points, calib["rect"],
calib["Trv2c"],
calib["P2"], image_shape)
if self.remove_environment is True and self.mode == "train":
selected = keep_arrays_by_name(gt_names, target_assigner.classes)
_dict_select(gt_dict, selected)
masks = box_np_ops.points_in_rbbox(points, gt_dict["gt_boxes"])
points = points[masks.any(-1)]
if self.mode == "train":
selected = drop_arrays_by_name(gt_dict["gt_names"],
["DontCare", "ignore"])
_dict_select(gt_dict, selected)
if self.remove_unknown:
remove_mask = gt_dict["difficulty"] == -1
"""
gt_boxes_remove = gt_boxes[remove_mask]
gt_boxes_remove[:, 3:6] += 0.25
points = prep.remove_points_in_boxes(points, gt_boxes_remove)
"""
keep_mask = np.logical_not(remove_mask)
_dict_select(gt_dict, keep_mask)
gt_dict.pop("difficulty")
if self.min_points_in_gt > 0:
# points_count_rbbox takes 10ms with 10 sweeps nuscenes data
point_counts = box_np_ops.points_count_rbbox(
points, gt_dict["gt_boxes"])
mask = point_counts >= min_points_in_gt
_dict_select(gt_dict, mask)
gt_boxes_mask = np.array(
[n in self.class_names for n in gt_dict["gt_names"]],
dtype=np.bool_)
if self.db_sampler:
sampled_dict = self.db_sampler.sample_all(
res["metadata"]["image_prefix"],
gt_dict["gt_boxes"],
gt_dict["gt_names"],
res["metadata"]["num_point_features"],
self.random_crop,
gt_group_ids=None,
calib=calib,
road_planes=None # res["lidar"]["ground_plane"]
)
if sampled_dict is not None:
sampled_gt_names = sampled_dict["gt_names"]
sampled_gt_boxes = sampled_dict["gt_boxes"]
sampled_points = sampled_dict["points"]
sampled_gt_masks = sampled_dict["gt_masks"]
gt_dict["gt_names"] = np.concatenate(
[gt_dict["gt_names"], sampled_gt_names], axis=0)
gt_dict["gt_boxes"] = np.concatenate(
[gt_dict["gt_boxes"], sampled_gt_boxes])
gt_boxes_mask = np.concatenate(
[gt_boxes_mask, sampled_gt_masks], axis=0)
if self.remove_points_after_sample:
masks = box_np_ops.points_in_rbbox(
points, sampled_gt_boxes)
points = points[np.logical_not(masks.any(-1))]
points = np.concatenate([sampled_points, points], axis=0)
prep.noise_per_object_v3_(
gt_dict["gt_boxes"],
points,
gt_boxes_mask,
rotation_perturb=self.gt_rotation_noise,
center_noise_std=self.gt_loc_noise_std,
global_random_rot_range=self.global_random_rot_range,
group_ids=None,
num_try=100,
)
_dict_select(gt_dict, gt_boxes_mask)
gt_classes = np.array(
[self.class_names.index(n) + 1 for n in gt_dict["gt_names"]],
dtype=np.int32,
)
gt_dict["gt_classes"] = gt_classes
iskitti = res["type"] in ["KittiDataset"]
if self.kitti_double:
assert False, "No more KITTI"
gt_dict["gt_boxes"], points = prep.random_flip_both(
gt_dict["gt_boxes"], points, flip_coor=70.4 / 2)
elif self.flip_single or iskitti:
assert False, "nuscenes double flip is better"
gt_dict["gt_boxes"], points = prep.random_flip(
gt_dict["gt_boxes"], points)
else:
gt_dict["gt_boxes"], points = prep.random_flip_both(
gt_dict["gt_boxes"], points)
gt_dict["gt_boxes"], points = prep.global_rotation(
gt_dict["gt_boxes"],
points,
rotation=self.global_rotation_noise)
gt_dict["gt_boxes"], points = prep.global_scaling_v2(
gt_dict["gt_boxes"], points, *self.global_scaling_noise)
if self.shuffle_points:
# shuffle is a little slow.
np.random.shuffle(points)
if self.mode == "train" and self.random_select:
if self.npoints < points.shape[0]:
pts_depth = points[:, 2]
pts_near_flag = pts_depth < 40.0
far_idxs_choice = np.where(pts_near_flag == 0)[0]
near_idxs = np.where(pts_near_flag == 1)[0]
near_idxs_choice = np.random.choice(near_idxs,
self.npoints -
len(far_idxs_choice),
replace=False)
choice = (np.concatenate(
(near_idxs_choice, far_idxs_choice), axis=0)
if len(far_idxs_choice) > 0 else near_idxs_choice)
np.random.shuffle(choice)
else:
choice = np.arange(0, len(points), dtype=np.int32)
if self.npoints > len(points):
extra_choice = np.random.choice(choice,
self.npoints - len(points),
replace=False)
choice = np.concatenate((choice, extra_choice), axis=0)
np.random.shuffle(choice)
points = points[choice]
if self.symmetry_intensity:
points[:, -1] -= 0.5 # translate intensity to [-0.5, 0.5]
# points[:, -1] *= 2
if self.normalize_intensity and res["type"] in ["NuScenesDataset"]:
# print(points[:20, 3])
assert 0, "Velocity Accuracy drops 3 percent with normalization.."
points[:, 3] /= 255
res["lidar"]["points"] = points
if self.mode == "train":
res["lidar"]["annotations"] = gt_dict
return res, info
def __call__(self, res, info, res_1, info_1, res_2, info_2):
res["mode"] = self.mode
res_1["mode"] = self.mode
res_2["mode"] = self.mode
if res["type"] in ["KittiDataset", "LyftDataset", "LvxDataset"]:
points = res["lidar"]["points"]
points_1 = res_1["lidar"]["points"]
points_2 = res_2["lidar"]["points"]
elif res["type"] == "NuScenesDataset":
points = res["lidar"]["combined"]
if self.mode == "train":
anno_dict = res["lidar"]["annotations"]
gt_dict = {
"gt_boxes": anno_dict["boxes"],
# 加入之前之后一帧的boxes
"gt_boxes_1": anno_dict["boxes_1"],
"gt_boxes_2": anno_dict["boxes_2"],
"gt_boxes_3": anno_dict["boxes_3"],
"gt_names": np.array(anno_dict["names"]).reshape(-1),
}
if "difficulty" not in anno_dict:
difficulty = np.zeros([anno_dict["boxes"].shape[0]],
dtype=np.int32)
gt_dict["difficulty"] = difficulty
else:
gt_dict["difficulty"] = anno_dict["difficulty"]
if "calib" in res:
calib = res["calib"]
else:
calib = None
if self.add_rgb_to_points:
assert calib is not None and "image" in res
image_path = res["image"]["image_path"]
image = (imgio.imread(str(pathlib.Path(root_path) /
image_path)).astype(np.float32) / 255)
points_rgb = box_np_ops.add_rgb_to_points(points, image,
calib["rect"],
calib["Trv2c"],
calib["P2"])
points = np.concatenate([points, points_rgb], axis=1)
num_point_features += 3
if self.reference_detections is not None:
assert calib is not None and "image" in res
C, R, T = box_np_ops.projection_matrix_to_CRT_kitti(P2)
frustums = box_np_ops.get_frustum_v2(reference_detections, C)
frustums -= T
frustums = np.einsum("ij, akj->aki", np.linalg.inv(R), frustums)
frustums = box_np_ops.camera_to_lidar(frustums, rect, Trv2c)
surfaces = box_np_ops.corner_to_surfaces_3d_jit(frustums)
masks = points_in_convex_polygon_3d_jit(points, surfaces)
points = points[masks.any(-1)]
if self.remove_outside_points:
assert calib is not None
image_shape = res["image"]["image_shape"]
points = box_np_ops.remove_outside_points(points, calib["rect"],
calib["Trv2c"],
calib["P2"], image_shape)
if self.remove_environment is True and self.mode == "train":
selected = kitti.keep_arrays_by_name(gt_names,
target_assigner.classes)
_dict_select(gt_dict, selected)
masks = box_np_ops.points_in_rbbox(points, gt_dict["gt_boxes"])
points = points[masks.any(-1)]
if self.mode == "train":
selected = kitti.drop_arrays_by_name(gt_dict["gt_names"],
["DontCare", "ignore"])
_dict_select(gt_dict, selected)
if self.remove_unknown:
remove_mask = gt_dict["difficulty"] == -1
"""
gt_boxes_remove = gt_boxes[remove_mask]
gt_boxes_remove[:, 3:6] += 0.25
points = prep.remove_points_in_boxes(points, gt_boxes_remove)
"""
keep_mask = np.logical_not(remove_mask)
_dict_select(gt_dict, keep_mask)
gt_dict.pop("difficulty")
# 保证每个box内点的数量
if self.min_points_in_gt > 0:
# points_count_rbbox takes 10ms with 10 sweeps nuscenes data
point_counts = box_np_ops.points_count_rbbox(
points, gt_dict["gt_boxes"])
mask = point_counts >= min_points_in_gt
_dict_select(gt_dict, mask)
gt_boxes_mask = np.array(
[n in self.class_names for n in gt_dict["gt_names"]],
dtype=np.bool_)
# 数据增广暂时去掉，有点改不过来
if self.db_sampler:
pass
assert NotImplementedError
sampled_dict = self.db_sampler.sample_all(
res["metadata"]["image_prefix"],
gt_dict["gt_boxes"],
gt_dict["gt_names"],
res["metadata"]["num_point_features"],
self.random_crop,
gt_group_ids=None,
calib=calib,
)
if sampled_dict is not None:
sampled_gt_names = sampled_dict["gt_names"]
sampled_gt_boxes = sampled_dict["gt_boxes"]
sampled_points = sampled_dict["points"]
sampled_gt_masks = sampled_dict["gt_masks"]
gt_dict["gt_names"] = np.concatenate(
[gt_dict["gt_names"], sampled_gt_names], axis=0)
gt_dict["gt_boxes"] = np.concatenate(
[gt_dict["gt_boxes"], sampled_gt_boxes])
gt_boxes_mask = np.concatenate(
[gt_boxes_mask, sampled_gt_masks], axis=0)
if self.remove_points_after_sample:
masks = box_np_ops.points_in_rbbox(
points, sampled_gt_boxes)
points = points[np.logical_not(masks.any(-1))]
points = np.concatenate([sampled_points, points], axis=0)
# 暂时不加扰动了
# TODO:需要改4帧，t-2，t-1,t的点云，以及t+1的box
prep.noise_per_object_v3_(
gt_dict["gt_boxes"],
gt_dict["gt_boxes_1"],
gt_dict["gt_boxes_2"],
gt_dict["gt_boxes_3"],
points,
points_1,
points_2,
gt_boxes_mask,
rotation_perturb=self.gt_rotation_noise,
center_noise_std=self.gt_loc_noise_std,
global_random_rot_range=self.global_random_rot_range,
group_ids=None,
num_try=100,
)
_dict_select(gt_dict, gt_boxes_mask)
# 将类别转换为index
gt_classes = np.array(
[self.class_names.index(n) + 1 for n in gt_dict["gt_names"]],
dtype=np.int32,
)
gt_dict["gt_classes"] = gt_classes
# 添加了三帧的全局变换
gt_dict["gt_boxes"], gt_dict["gt_boxes_1"], gt_dict[
"gt_boxes_2"], points, points_1, points_2 = prep.random_flip(
gt_dict["gt_boxes"], gt_dict["gt_boxes_1"],
gt_dict["gt_boxes_2"], points, points_1, points_2)
gt_dict["gt_boxes"], gt_dict["gt_boxes_1"], gt_dict[
"gt_boxes_2"], points, points_1, points_2 = prep.global_rotation(
gt_dict["gt_boxes"], gt_dict["gt_boxes_1"],
gt_dict["gt_boxes_2"],
points,
points_1,
points_2,
rotation=self.global_rotation_noise)
gt_dict["gt_boxes"], gt_dict["gt_boxes_1"], gt_dict[
"gt_boxes_2"], points, points_1, points_2 = prep.global_scaling_v2(
gt_dict["gt_boxes"], gt_dict["gt_boxes_1"],
gt_dict["gt_boxes_2"], points, points_1, points_2, *self.global_scaling_noise)
if self.shuffle_points:
# shuffle is a little slow.
np.random.shuffle(points)
np.random.shuffle(points_1)
np.random.shuffle(points_2)
if self.mode == "train" and self.random_select:
# 进行点的随机采样，暂时不需要
if self.npoints < points.shape[0]:
pts_depth = points[:, 2]
pts_near_flag = pts_depth < 40.0
far_idxs_choice = np.where(pts_near_flag == 0)[0]
near_idxs = np.where(pts_near_flag == 1)[0]
near_idxs_choice = np.random.choice(near_idxs,
self.npoints -
len(far_idxs_choice),
replace=False)
choice = (np.concatenate(
(near_idxs_choice, far_idxs_choice), axis=0)
if len(far_idxs_choice) > 0 else near_idxs_choice)
np.random.shuffle(choice)
else:
choice = np.arange(0, len(points), dtype=np.int32)
if self.npoints > len(points):
extra_choice = np.random.choice(choice,
self.npoints - len(points),
replace=False)
choice = np.concatenate((choice, extra_choice), axis=0)
np.random.shuffle(choice)
points = points[choice]
if self.symmetry_intensity:
points[:, -1] -= 0.5 # translate intensity to [-0.5, 0.5]
# points[:, -1] *= 2
res["lidar"]["points"] = points
res_1["lidar"]["points"] = points_1
res_2["lidar"]["points"] = points_2
if self.mode == "train":
import copy
res["lidar"]["annotations"] = gt_dict
res_1["lidar"]["annotations"] = copy.deepcopy(gt_dict)
res_2["lidar"]["annotations"] = copy.deepcopy(gt_dict)
return res, info, res_1,info_1,res_2,info_2