-
Notifications
You must be signed in to change notification settings - Fork 1.6k
/
Copy pathbox_3d_mode.py
197 lines (171 loc) · 7 KB
/
box_3d_mode.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
# Copyright (c) OpenMMLab. All rights reserved.
from enum import IntEnum, unique
import numpy as np
import torch
from .base_box3d import BaseInstance3DBoxes
from .cam_box3d import CameraInstance3DBoxes
from .depth_box3d import DepthInstance3DBoxes
from .lidar_box3d import LiDARInstance3DBoxes
from .utils import limit_period
@unique
class Box3DMode(IntEnum):
r"""Enum of different ways to represent a box.
Coordinates in LiDAR:
.. code-block:: none
up z
^ x front
| /
| /
left y <------ 0
The relative coordinate of bottom center in a LiDAR box is (0.5, 0.5, 0),
and the yaw is around the z axis, thus the rotation axis=2.
Coordinates in camera:
.. code-block:: none
z front
/
/
0 ------> x right
|
|
v
down y
The relative coordinate of bottom center in a CAM box is [0.5, 1.0, 0.5],
and the yaw is around the y axis, thus the rotation axis=1.
Coordinates in Depth mode:
.. code-block:: none
up z
^ y front
| /
| /
0 ------> x right
The relative coordinate of bottom center in a DEPTH box is (0.5, 0.5, 0),
and the yaw is around the z axis, thus the rotation axis=2.
"""
LIDAR = 0
CAM = 1
DEPTH = 2
@staticmethod
def convert(box, src, dst, rt_mat=None, with_yaw=True):
"""Convert boxes from `src` mode to `dst` mode.
Args:
box (tuple | list | np.ndarray |
torch.Tensor | :obj:`BaseInstance3DBoxes`):
Can be a k-tuple, k-list or an Nxk array/tensor, where k = 7.
src (:obj:`Box3DMode`): The src Box mode.
dst (:obj:`Box3DMode`): The target Box mode.
rt_mat (np.ndarray | torch.Tensor, optional): The rotation and
translation matrix between different coordinates.
Defaults to None.
The conversion from `src` coordinates to `dst` coordinates
usually comes along the change of sensors, e.g., from camera
to LiDAR. This requires a transformation matrix.
with_yaw (bool, optional): If `box` is an instance of
:obj:`BaseInstance3DBoxes`, whether or not it has a yaw angle.
Defaults to True.
Returns:
(tuple | list | np.ndarray | torch.Tensor |
:obj:`BaseInstance3DBoxes`):
The converted box of the same type.
"""
if src == dst:
return box
is_numpy = isinstance(box, np.ndarray)
is_Instance3DBoxes = isinstance(box, BaseInstance3DBoxes)
single_box = isinstance(box, (list, tuple))
if single_box:
assert len(box) >= 7, (
'Box3DMode.convert takes either a k-tuple/list or '
'an Nxk array/tensor, where k >= 7')
arr = torch.tensor(box)[None, :]
else:
# avoid modifying the input box
if is_numpy:
arr = torch.from_numpy(np.asarray(box)).clone()
elif is_Instance3DBoxes:
arr = box.tensor.clone()
else:
arr = box.clone()
if is_Instance3DBoxes:
with_yaw = box.with_yaw
# convert box from `src` mode to `dst` mode.
x_size, y_size, z_size = arr[..., 3:4], arr[..., 4:5], arr[..., 5:6]
if with_yaw:
yaw = arr[..., 6:7]
if src == Box3DMode.LIDAR and dst == Box3DMode.CAM:
if rt_mat is None:
rt_mat = arr.new_tensor([[0, -1, 0], [0, 0, -1], [1, 0, 0]])
xyz_size = torch.cat([x_size, z_size, y_size], dim=-1)
if with_yaw:
yaw = -yaw - np.pi / 2
yaw = limit_period(yaw, period=np.pi * 2)
elif src == Box3DMode.CAM and dst == Box3DMode.LIDAR:
if rt_mat is None:
rt_mat = arr.new_tensor([[0, 0, 1], [-1, 0, 0], [0, -1, 0]])
xyz_size = torch.cat([x_size, z_size, y_size], dim=-1)
if with_yaw:
yaw = -yaw - np.pi / 2
yaw = limit_period(yaw, period=np.pi * 2)
elif src == Box3DMode.DEPTH and dst == Box3DMode.CAM:
if rt_mat is None:
rt_mat = arr.new_tensor([[1, 0, 0], [0, 0, -1], [0, 1, 0]])
xyz_size = torch.cat([x_size, z_size, y_size], dim=-1)
if with_yaw:
yaw = -yaw
elif src == Box3DMode.CAM and dst == Box3DMode.DEPTH:
if rt_mat is None:
rt_mat = arr.new_tensor([[1, 0, 0], [0, 0, 1], [0, -1, 0]])
xyz_size = torch.cat([x_size, z_size, y_size], dim=-1)
if with_yaw:
yaw = -yaw
elif src == Box3DMode.LIDAR and dst == Box3DMode.DEPTH:
if rt_mat is None:
rt_mat = arr.new_tensor([[0, -1, 0], [1, 0, 0], [0, 0, 1]])
xyz_size = torch.cat([x_size, y_size, z_size], dim=-1)
if with_yaw:
yaw = yaw + np.pi / 2
yaw = limit_period(yaw, period=np.pi * 2)
elif src == Box3DMode.DEPTH and dst == Box3DMode.LIDAR:
if rt_mat is None:
rt_mat = arr.new_tensor([[0, 1, 0], [-1, 0, 0], [0, 0, 1]])
xyz_size = torch.cat([x_size, y_size, z_size], dim=-1)
if with_yaw:
yaw = yaw - np.pi / 2
yaw = limit_period(yaw, period=np.pi * 2)
else:
raise NotImplementedError(
f'Conversion from Box3DMode {src} to {dst} '
'is not supported yet')
if not isinstance(rt_mat, torch.Tensor):
rt_mat = arr.new_tensor(rt_mat)
if rt_mat.size(1) == 4:
extended_xyz = torch.cat(
[arr[..., :3], arr.new_ones(arr.size(0), 1)], dim=-1)
xyz = extended_xyz @ rt_mat.t()
else:
xyz = arr[..., :3] @ rt_mat.t()
if with_yaw:
remains = arr[..., 7:]
arr = torch.cat([xyz[..., :3], xyz_size, yaw, remains], dim=-1)
else:
remains = arr[..., 6:]
arr = torch.cat([xyz[..., :3], xyz_size, remains], dim=-1)
# convert arr to the original type
original_type = type(box)
if single_box:
return original_type(arr.flatten().tolist())
if is_numpy:
return arr.numpy()
elif is_Instance3DBoxes:
if dst == Box3DMode.CAM:
target_type = CameraInstance3DBoxes
elif dst == Box3DMode.LIDAR:
target_type = LiDARInstance3DBoxes
elif dst == Box3DMode.DEPTH:
target_type = DepthInstance3DBoxes
else:
raise NotImplementedError(
f'Conversion to {dst} through {original_type}'
' is not supported yet')
return target_type(arr, box_dim=arr.size(-1), with_yaw=with_yaw)
else:
return arr