transforms_3d.py 23.3 KB
Newer Older
zhangwenwei's avatar
zhangwenwei committed
1
import numpy as np
2
from mmcv.utils import build_from_cfg
zhangwenwei's avatar
zhangwenwei committed
3
4

from mmdet3d.core.bbox import box_np_ops
5
from mmdet.datasets.builder import PIPELINES
zhangwenwei's avatar
zhangwenwei committed
6
from mmdet.datasets.pipelines import RandomFlip
zhangwenwei's avatar
zhangwenwei committed
7
8
9
10
from ..registry import OBJECTSAMPLERS
from .data_augment_utils import noise_per_object_v3_


11
@PIPELINES.register_module()
zhangwenwei's avatar
zhangwenwei committed
12
13
14
15
16
17
18
19
class RandomFlip3D(RandomFlip):
    """Flip the points & bbox.

    If the input dict contains the key "flip", then the flag will be used,
    otherwise it will be randomly decided by a ratio specified in the init
    method.

    Args:
zhangwenwei's avatar
zhangwenwei committed
20
21
22
        sync_2d (bool, optional): Whether to apply flip according to the 2D
            images. If True, it will apply the same flip as that to 2D images.
            If False, it will decide whether to flip randomly and independently
liyinhao's avatar
liyinhao committed
23
            to that of 2D images. Defaults to True.
wuyuefeng's avatar
wuyuefeng committed
24
        flip_ratio_bev_horizontal (float, optional): The flipping probability
liyinhao's avatar
liyinhao committed
25
            in horizontal direction. Defaults to 0.0.
wuyuefeng's avatar
wuyuefeng committed
26
        flip_ratio_bev_vertical (float, optional): The flipping probability
liyinhao's avatar
liyinhao committed
27
            in vertical direction. Defaults to 0.0.
zhangwenwei's avatar
zhangwenwei committed
28
29
    """

wuyuefeng's avatar
wuyuefeng committed
30
31
32
33
34
35
36
    def __init__(self,
                 sync_2d=True,
                 flip_ratio_bev_horizontal=0.0,
                 flip_ratio_bev_vertical=0.0,
                 **kwargs):
        super(RandomFlip3D, self).__init__(
            flip_ratio=flip_ratio_bev_horizontal, **kwargs)
zhangwenwei's avatar
zhangwenwei committed
37
        self.sync_2d = sync_2d
wuyuefeng's avatar
wuyuefeng committed
38
39
40
41
42
43
44
45
46
47
48
        self.flip_ratio_bev_vertical = flip_ratio_bev_vertical
        if flip_ratio_bev_horizontal is not None:
            assert isinstance(
                flip_ratio_bev_horizontal,
                (int, float)) and 0 <= flip_ratio_bev_horizontal <= 1
        if flip_ratio_bev_vertical is not None:
            assert isinstance(
                flip_ratio_bev_vertical,
                (int, float)) and 0 <= flip_ratio_bev_vertical <= 1

    def random_flip_data_3d(self, input_dict, direction='horizontal'):
49
50
51
52
53
54
55
56
57
58
        """Flip 3D data randomly.

        Args:
            input_dict (dict): Result dict from loading pipeline.
            direction (str): Flip direction. Default: horizontal.

        Returns:
            dict: Flipped results, 'points', 'bbox3d_fields' keys are \
                updated in the result dict.
        """
wuyuefeng's avatar
wuyuefeng committed
59
        assert direction in ['horizontal', 'vertical']
60
61
62
63
64
        if len(input_dict['bbox3d_fields']) == 0:  # test mode
            input_dict['bbox3d_fields'].append('empty_box3d')
            input_dict['empty_box3d'] = input_dict['box_type_3d'](
                np.array([], dtype=np.float32))
        assert len(input_dict['bbox3d_fields']) == 1
zhangwenwei's avatar
zhangwenwei committed
65
        for key in input_dict['bbox3d_fields']:
wuyuefeng's avatar
wuyuefeng committed
66
67
            input_dict['points'] = input_dict[key].flip(
                direction, points=input_dict['points'])
zhangwenwei's avatar
zhangwenwei committed
68
69

    def __call__(self, input_dict):
70
71
72
73
74
75
76
77
78
79
80
        """Call function to flip points, values in the ``bbox3d_fields`` and \
        also flip 2D image and its annotations.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Flipped results, 'flip', 'flip_direction', \
                'pcd_horizontal_flip' and 'pcd_vertical_flip' keys are added \
                into result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
81
        # filp 2D image and its annotations
zhangwenwei's avatar
zhangwenwei committed
82
        super(RandomFlip3D, self).__call__(input_dict)
zhangwenwei's avatar
zhangwenwei committed
83

zhangwenwei's avatar
zhangwenwei committed
84
        if self.sync_2d:
wuyuefeng's avatar
wuyuefeng committed
85
86
            input_dict['pcd_horizontal_flip'] = input_dict['flip']
            input_dict['pcd_vertical_flip'] = False
zhangwenwei's avatar
zhangwenwei committed
87
        else:
wuyuefeng's avatar
wuyuefeng committed
88
89
90
91
92
93
94
95
96
97
98
99
100
            if 'pcd_horizontal_flip' not in input_dict:
                flip_horizontal = True if np.random.rand(
                ) < self.flip_ratio else False
                input_dict['pcd_horizontal_flip'] = flip_horizontal
            if 'pcd_vertical_flip' not in input_dict:
                flip_vertical = True if np.random.rand(
                ) < self.flip_ratio_bev_vertical else False
                input_dict['pcd_vertical_flip'] = flip_vertical

        if input_dict['pcd_horizontal_flip']:
            self.random_flip_data_3d(input_dict, 'horizontal')
        if input_dict['pcd_vertical_flip']:
            self.random_flip_data_3d(input_dict, 'vertical')
zhangwenwei's avatar
zhangwenwei committed
101
102
        return input_dict

zhangwenwei's avatar
zhangwenwei committed
103
    def __repr__(self):
104
        """str: Return a string that describes the module."""
wuyuefeng's avatar
wuyuefeng committed
105
106
107
108
109
110
111
        repr_str = self.__class__.__name__
        repr_str += '(sync_2d={},'.format(self.sync_2d)
        repr_str += '(flip_ratio_bev_horizontal={},'.format(
            self.flip_ratio_bev_horizontal)
        repr_str += '(flip_ratio_bev_vertical={},'.format(
            self.flip_ratio_bev_vertical)
        return repr_str
zhangwenwei's avatar
zhangwenwei committed
112

zhangwenwei's avatar
zhangwenwei committed
113

114
@PIPELINES.register_module()
zhangwenwei's avatar
zhangwenwei committed
115
class ObjectSample(object):
zhangwenwei's avatar
zhangwenwei committed
116
    """Sample GT objects to the data.
zhangwenwei's avatar
zhangwenwei committed
117
118
119
120
121

    Args:
        db_sampler (dict): Config dict of the database sampler.
        sample_2d (bool): Whether to also paste 2D image patch to the images
            This should be true when applying multi-modality cut-and-paste.
liyinhao's avatar
liyinhao committed
122
            Defaults to False.
zhangwenwei's avatar
zhangwenwei committed
123
    """
zhangwenwei's avatar
zhangwenwei committed
124
125
126
127
128
129
130
131
132
133

    def __init__(self, db_sampler, sample_2d=False):
        self.sampler_cfg = db_sampler
        self.sample_2d = sample_2d
        if 'type' not in db_sampler.keys():
            db_sampler['type'] = 'DataBaseSampler'
        self.db_sampler = build_from_cfg(db_sampler, OBJECTSAMPLERS)

    @staticmethod
    def remove_points_in_boxes(points, boxes):
134
135
136
137
138
139
140
141
142
        """Remove the points in the sampled bounding boxes.

        Args:
            points (np.ndarray): Input point cloud array.
            boxes (np.ndarray): Sampled ground truth boxes.

        Returns:
            np.ndarray: Points with those in the boxes removed.
        """
zhangwenwei's avatar
zhangwenwei committed
143
144
145
146
147
        masks = box_np_ops.points_in_rbbox(points, boxes)
        points = points[np.logical_not(masks.any(-1))]
        return points

    def __call__(self, input_dict):
148
149
150
151
152
153
154
155
156
157
        """Call function to sample ground truth objects to the data.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after object sampling augmentation, \
                'points', 'gt_bboxes_3d', 'gt_labels_3d' keys are updated \
                in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
158
        gt_bboxes_3d = input_dict['gt_bboxes_3d']
zhangwenwei's avatar
zhangwenwei committed
159
160
        gt_labels_3d = input_dict['gt_labels_3d']

zhangwenwei's avatar
zhangwenwei committed
161
162
163
        # change to float for blending operation
        points = input_dict['points']
        if self.sample_2d:
wuyuefeng's avatar
wuyuefeng committed
164
            img = input_dict['img']
zhangwenwei's avatar
zhangwenwei committed
165
166
167
            gt_bboxes_2d = input_dict['gt_bboxes']
            # Assume for now 3D & 2D bboxes are the same
            sampled_dict = self.db_sampler.sample_all(
168
169
170
171
                gt_bboxes_3d.tensor.numpy(),
                gt_labels_3d,
                gt_bboxes_2d=gt_bboxes_2d,
                img=img)
zhangwenwei's avatar
zhangwenwei committed
172
173
        else:
            sampled_dict = self.db_sampler.sample_all(
174
                gt_bboxes_3d.tensor.numpy(), gt_labels_3d, img=None)
zhangwenwei's avatar
zhangwenwei committed
175
176
177
178

        if sampled_dict is not None:
            sampled_gt_bboxes_3d = sampled_dict['gt_bboxes_3d']
            sampled_points = sampled_dict['points']
zhangwenwei's avatar
zhangwenwei committed
179
            sampled_gt_labels = sampled_dict['gt_labels_3d']
zhangwenwei's avatar
zhangwenwei committed
180

zhangwenwei's avatar
zhangwenwei committed
181
182
            gt_labels_3d = np.concatenate([gt_labels_3d, sampled_gt_labels],
                                          axis=0)
183
184
185
            gt_bboxes_3d = gt_bboxes_3d.new_box(
                np.concatenate(
                    [gt_bboxes_3d.tensor.numpy(), sampled_gt_bboxes_3d]))
zhangwenwei's avatar
zhangwenwei committed
186

zhangwenwei's avatar
zhangwenwei committed
187
188
189
190
191
192
193
194
195
196
            points = self.remove_points_in_boxes(points, sampled_gt_bboxes_3d)
            # check the points dimension
            dim_inds = points.shape[-1]
            points = np.concatenate([sampled_points[:, :dim_inds], points],
                                    axis=0)

            if self.sample_2d:
                sampled_gt_bboxes_2d = sampled_dict['gt_bboxes_2d']
                gt_bboxes_2d = np.concatenate(
                    [gt_bboxes_2d, sampled_gt_bboxes_2d]).astype(np.float32)
zhangwenwei's avatar
zhangwenwei committed
197

zhangwenwei's avatar
zhangwenwei committed
198
                input_dict['gt_bboxes'] = gt_bboxes_2d
wuyuefeng's avatar
wuyuefeng committed
199
                input_dict['img'] = sampled_dict['img']
zhangwenwei's avatar
zhangwenwei committed
200
201

        input_dict['gt_bboxes_3d'] = gt_bboxes_3d
zhangwenwei's avatar
zhangwenwei committed
202
        input_dict['gt_labels_3d'] = gt_labels_3d
zhangwenwei's avatar
zhangwenwei committed
203
        input_dict['points'] = points
zhangwenwei's avatar
zhangwenwei committed
204

zhangwenwei's avatar
zhangwenwei committed
205
206
207
        return input_dict

    def __repr__(self):
208
        """str: Return a string that describes the module."""
209
210
211
212
213
214
215
216
217
        repr_str = self.__class__.__name__
        repr_str += f' sample_2d={self.sample_2d},'
        repr_str += f' data_root={self.sampler_cfg.data_root},'
        repr_str += f' info_path={self.sampler_cfg.info_path},'
        repr_str += f' rate={self.sampler_cfg.rate},'
        repr_str += f' prepare={self.sampler_cfg.prepare},'
        repr_str += f' classes={self.sampler_cfg.classes},'
        repr_str += f' sample_groups={self.sampler_cfg.sample_groups}'
        return repr_str
zhangwenwei's avatar
zhangwenwei committed
218
219


220
@PIPELINES.register_module()
zhangwenwei's avatar
zhangwenwei committed
221
class ObjectNoise(object):
zhangwenwei's avatar
zhangwenwei committed
222
    """Apply noise to each GT objects in the scene.
zhangwenwei's avatar
zhangwenwei committed
223
224

    Args:
225
        translation_std (list[float], optional): Standard deviation of the
zhangwenwei's avatar
zhangwenwei committed
226
227
            distribution where translation noise are sampled from.
            Defaults to [0.25, 0.25, 0.25].
228
        global_rot_range (list[float], optional): Global rotation to the scene.
zhangwenwei's avatar
zhangwenwei committed
229
            Defaults to [0.0, 0.0].
230
        rot_range (list[float], optional): Object rotation range.
zhangwenwei's avatar
zhangwenwei committed
231
232
233
234
            Defaults to [-0.15707963267, 0.15707963267].
        num_try (int, optional): Number of times to try if the noise applied is
            invalid. Defaults to 100.
    """
zhangwenwei's avatar
zhangwenwei committed
235
236

    def __init__(self,
zhangwenwei's avatar
zhangwenwei committed
237
                 translation_std=[0.25, 0.25, 0.25],
zhangwenwei's avatar
zhangwenwei committed
238
                 global_rot_range=[0.0, 0.0],
zhangwenwei's avatar
zhangwenwei committed
239
                 rot_range=[-0.15707963267, 0.15707963267],
zhangwenwei's avatar
zhangwenwei committed
240
                 num_try=100):
zhangwenwei's avatar
zhangwenwei committed
241
        self.translation_std = translation_std
zhangwenwei's avatar
zhangwenwei committed
242
        self.global_rot_range = global_rot_range
zhangwenwei's avatar
zhangwenwei committed
243
        self.rot_range = rot_range
zhangwenwei's avatar
zhangwenwei committed
244
245
246
        self.num_try = num_try

    def __call__(self, input_dict):
247
248
249
250
251
252
253
254
255
        """Call function to apply noise to each ground truth in the scene.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after adding noise to each object, \
                'points', 'gt_bboxes_3d' keys are updated in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
256
257
        gt_bboxes_3d = input_dict['gt_bboxes_3d']
        points = input_dict['points']
zhangwenwei's avatar
zhangwenwei committed
258

zhangwenwei's avatar
zhangwenwei committed
259
        # TODO: check this inplace function
260
        numpy_box = gt_bboxes_3d.tensor.numpy()
zhangwenwei's avatar
zhangwenwei committed
261
        noise_per_object_v3_(
262
            numpy_box,
zhangwenwei's avatar
zhangwenwei committed
263
            points,
zhangwenwei's avatar
zhangwenwei committed
264
265
            rotation_perturb=self.rot_range,
            center_noise_std=self.translation_std,
zhangwenwei's avatar
zhangwenwei committed
266
267
            global_random_rot_range=self.global_rot_range,
            num_try=self.num_try)
268
269

        input_dict['gt_bboxes_3d'] = gt_bboxes_3d.new_box(numpy_box)
zhangwenwei's avatar
zhangwenwei committed
270
271
272
273
        input_dict['points'] = points
        return input_dict

    def __repr__(self):
274
        """str: Return a string that describes the module."""
zhangwenwei's avatar
zhangwenwei committed
275
276
        repr_str = self.__class__.__name__
        repr_str += '(num_try={},'.format(self.num_try)
zhangwenwei's avatar
zhangwenwei committed
277
        repr_str += ' translation_std={},'.format(self.translation_std)
zhangwenwei's avatar
zhangwenwei committed
278
        repr_str += ' global_rot_range={},'.format(self.global_rot_range)
zhangwenwei's avatar
zhangwenwei committed
279
        repr_str += ' rot_range={})'.format(self.rot_range)
zhangwenwei's avatar
zhangwenwei committed
280
281
282
        return repr_str


283
@PIPELINES.register_module()
zhangwenwei's avatar
zhangwenwei committed
284
class GlobalRotScaleTrans(object):
zhangwenwei's avatar
zhangwenwei committed
285
    """Apply global rotation, scaling and translation to a 3D scene.
zhangwenwei's avatar
zhangwenwei committed
286
287
288

    Args:
        rot_range (list[float]): Range of rotation angle.
liyinhao's avatar
liyinhao committed
289
            Defaults to [-0.78539816, 0.78539816] (close to [-pi/4, pi/4]).
zhangwenwei's avatar
zhangwenwei committed
290
        scale_ratio_range (list[float]): Range of scale ratio.
liyinhao's avatar
liyinhao committed
291
            Defaults to [0.95, 1.05].
zhangwenwei's avatar
zhangwenwei committed
292
293
294
        translation_std (list[float]): The standard deviation of ranslation
            noise. This apply random translation to a scene by a noise, which
            is sampled from a gaussian distribution whose standard deviation
liyinhao's avatar
liyinhao committed
295
296
            is set by ``translation_std``. Defaults to [0, 0, 0]
        shift_height (bool): Whether to shift height.
wuyuefeng's avatar
wuyuefeng committed
297
            (the fourth dimension of indoor points) when scaling.
liyinhao's avatar
liyinhao committed
298
            Defaults to False.
zhangwenwei's avatar
zhangwenwei committed
299
    """
zhangwenwei's avatar
zhangwenwei committed
300
301

    def __init__(self,
zhangwenwei's avatar
zhangwenwei committed
302
303
                 rot_range=[-0.78539816, 0.78539816],
                 scale_ratio_range=[0.95, 1.05],
wuyuefeng's avatar
wuyuefeng committed
304
305
                 translation_std=[0, 0, 0],
                 shift_height=False):
zhangwenwei's avatar
zhangwenwei committed
306
307
308
        self.rot_range = rot_range
        self.scale_ratio_range = scale_ratio_range
        self.translation_std = translation_std
wuyuefeng's avatar
wuyuefeng committed
309
        self.shift_height = shift_height
zhangwenwei's avatar
zhangwenwei committed
310
311

    def _trans_bbox_points(self, input_dict):
312
313
314
315
316
317
318
319
320
321
        """Private function to translate bounding boxes and points.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after translation, 'points', 'pcd_trans' \
                and keys in input_dict['bbox3d_fields'] are updated \
                in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
        if not isinstance(self.translation_std, (list, tuple, np.ndarray)):
            translation_std = [
                self.translation_std, self.translation_std,
                self.translation_std
            ]
        else:
            translation_std = self.translation_std
        translation_std = np.array(translation_std, dtype=np.float32)
        trans_factor = np.random.normal(scale=translation_std, size=3).T

        input_dict['points'][:, :3] += trans_factor
        input_dict['pcd_trans'] = trans_factor
        for key in input_dict['bbox3d_fields']:
            input_dict[key].translate(trans_factor)

    def _rot_bbox_points(self, input_dict):
338
339
340
341
342
343
344
345
346
347
        """Private function to rotate bounding boxes and points.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after rotation, 'points', 'pcd_rotation' \
                and keys in input_dict['bbox3d_fields'] are updated \
                in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
348
        rotation = self.rot_range
zhangwenwei's avatar
zhangwenwei committed
349
350
351
        if not isinstance(rotation, list):
            rotation = [-rotation, rotation]
        noise_rotation = np.random.uniform(rotation[0], rotation[1])
zhangwenwei's avatar
zhangwenwei committed
352
353

        for key in input_dict['bbox3d_fields']:
wuyuefeng's avatar
wuyuefeng committed
354
355
356
357
358
            if len(input_dict[key].tensor) != 0:
                points, rot_mat_T = input_dict[key].rotate(
                    noise_rotation, input_dict['points'])
                input_dict['points'] = points
                input_dict['pcd_rotation'] = rot_mat_T
359

zhangwenwei's avatar
zhangwenwei committed
360
    def _scale_bbox_points(self, input_dict):
361
362
363
364
365
366
367
368
369
        """Private function to scale bounding boxes and points.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after scaling, 'points'and keys in \
                input_dict['bbox3d_fields'] are updated in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
370
371
        scale = input_dict['pcd_scale_factor']
        input_dict['points'][:, :3] *= scale
wuyuefeng's avatar
wuyuefeng committed
372
373
374
        if self.shift_height:
            input_dict['points'][:, -1] *= scale

zhangwenwei's avatar
zhangwenwei committed
375
376
        for key in input_dict['bbox3d_fields']:
            input_dict[key].scale(scale)
zhangwenwei's avatar
zhangwenwei committed
377

zhangwenwei's avatar
zhangwenwei committed
378
    def _random_scale(self, input_dict):
379
380
381
382
383
384
385
386
387
        """Private function to randomly set the scale factor.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after scaling, 'pcd_scale_factor' are updated \
                in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
388
389
390
        scale_factor = np.random.uniform(self.scale_ratio_range[0],
                                         self.scale_ratio_range[1])
        input_dict['pcd_scale_factor'] = scale_factor
zhangwenwei's avatar
zhangwenwei committed
391
392

    def __call__(self, input_dict):
393
394
395
396
397
398
399
400
401
402
403
        """Private function to rotate, scale and translate bounding boxes and \
        points.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after scaling, 'points', 'pcd_rotation',
                'pcd_scale_factor', 'pcd_trans' and keys in \
                input_dict['bbox3d_fields'] are updated in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
404
        self._rot_bbox_points(input_dict)
zhangwenwei's avatar
zhangwenwei committed
405

zhangwenwei's avatar
zhangwenwei committed
406
407
408
        if 'pcd_scale_factor' not in input_dict:
            self._random_scale(input_dict)
        self._scale_bbox_points(input_dict)
zhangwenwei's avatar
zhangwenwei committed
409

zhangwenwei's avatar
zhangwenwei committed
410
        self._trans_bbox_points(input_dict)
zhangwenwei's avatar
zhangwenwei committed
411
412
413
        return input_dict

    def __repr__(self):
414
        """str: Return a string that describes the module."""
zhangwenwei's avatar
zhangwenwei committed
415
        repr_str = self.__class__.__name__
zhangwenwei's avatar
zhangwenwei committed
416
417
418
        repr_str += '(rot_range={},'.format(self.rot_range)
        repr_str += ' scale_ratio_range={},'.format(self.scale_ratio_range)
        repr_str += ' translation_std={})'.format(self.translation_std)
wuyuefeng's avatar
wuyuefeng committed
419
        repr_str += ' shift_height={})'.format(self.shift_height)
zhangwenwei's avatar
zhangwenwei committed
420
421
422
        return repr_str


423
@PIPELINES.register_module()
zhangwenwei's avatar
zhangwenwei committed
424
class PointShuffle(object):
425
    """Shuffle input points."""
zhangwenwei's avatar
zhangwenwei committed
426
427

    def __call__(self, input_dict):
428
429
430
431
432
433
434
435
436
        """Call function to shuffle points.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after filtering, 'points' keys are updated \
                in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
437
438
439
440
441
442
443
        np.random.shuffle(input_dict['points'])
        return input_dict

    def __repr__(self):
        return self.__class__.__name__


444
@PIPELINES.register_module()
zhangwenwei's avatar
zhangwenwei committed
445
class ObjectRangeFilter(object):
446
447
448
449
450
    """Filter objects by the range.

    Args:
        point_cloud_range (list[float]): Point cloud range.
    """
zhangwenwei's avatar
zhangwenwei committed
451
452
453
454
455
456

    def __init__(self, point_cloud_range):
        self.pcd_range = np.array(point_cloud_range, dtype=np.float32)
        self.bev_range = self.pcd_range[[0, 1, 3, 4]]

    def __call__(self, input_dict):
457
458
459
460
461
462
463
464
465
        """Call function to filter objects by the range.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after filtering, 'gt_bboxes_3d', 'gt_labels_3d' \
                keys are updated in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
466
        gt_bboxes_3d = input_dict['gt_bboxes_3d']
zhangwenwei's avatar
zhangwenwei committed
467
        gt_labels_3d = input_dict['gt_labels_3d']
468
        mask = gt_bboxes_3d.in_range_bev(self.bev_range)
zhangwenwei's avatar
zhangwenwei committed
469
        gt_bboxes_3d = gt_bboxes_3d[mask]
ZwwWayne's avatar
ZwwWayne committed
470
471
472
473
474
        # mask is a torch tensor but gt_labels_3d is still numpy array
        # using mask to index gt_labels_3d will cause bug when
        # len(gt_labels_3d) == 1, where mask=1 will be interpreted
        # as gt_labels_3d[1] and cause out of index error
        gt_labels_3d = gt_labels_3d[mask.numpy().astype(np.bool)]
zhangwenwei's avatar
zhangwenwei committed
475
476

        # limit rad to [-pi, pi]
477
478
        gt_bboxes_3d.limit_yaw(offset=0.5, period=2 * np.pi)
        input_dict['gt_bboxes_3d'] = gt_bboxes_3d
zhangwenwei's avatar
zhangwenwei committed
479
480
        input_dict['gt_labels_3d'] = gt_labels_3d

zhangwenwei's avatar
zhangwenwei committed
481
482
483
        return input_dict

    def __repr__(self):
484
        """str: Return a string that describes the module."""
zhangwenwei's avatar
zhangwenwei committed
485
486
487
488
489
        repr_str = self.__class__.__name__
        repr_str += '(point_cloud_range={})'.format(self.pcd_range.tolist())
        return repr_str


490
@PIPELINES.register_module()
zhangwenwei's avatar
zhangwenwei committed
491
class PointsRangeFilter(object):
492
493
494
495
496
    """Filter points by the range.

    Args:
        point_cloud_range (list[float]): Point cloud range.
    """
zhangwenwei's avatar
zhangwenwei committed
497
498
499
500
501
502

    def __init__(self, point_cloud_range):
        self.pcd_range = np.array(
            point_cloud_range, dtype=np.float32)[np.newaxis, :]

    def __call__(self, input_dict):
503
504
505
506
507
508
509
510
511
        """Call function to filter points by the range.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after filtering, 'points' keys are updated \
                in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
512
513
514
515
516
517
518
519
520
        points = input_dict['points']
        points_mask = ((points[:, :3] >= self.pcd_range[:, :3])
                       & (points[:, :3] < self.pcd_range[:, 3:]))
        points_mask = points_mask[:, 0] & points_mask[:, 1] & points_mask[:, 2]
        clean_points = points[points_mask, :]
        input_dict['points'] = clean_points
        return input_dict

    def __repr__(self):
521
        """str: Return a string that describes the module."""
zhangwenwei's avatar
zhangwenwei committed
522
523
524
        repr_str = self.__class__.__name__
        repr_str += '(point_cloud_range={})'.format(self.pcd_range.tolist())
        return repr_str
zhangwenwei's avatar
zhangwenwei committed
525
526
527
528


@PIPELINES.register_module()
class ObjectNameFilter(object):
zhangwenwei's avatar
zhangwenwei committed
529
    """Filter GT objects by their names.
zhangwenwei's avatar
zhangwenwei committed
530
531

    Args:
liyinhao's avatar
liyinhao committed
532
        classes (list[str]): List of class names to be kept for training.
zhangwenwei's avatar
zhangwenwei committed
533
534
535
536
537
538
539
    """

    def __init__(self, classes):
        self.classes = classes
        self.labels = list(range(len(self.classes)))

    def __call__(self, input_dict):
540
541
542
543
544
545
546
547
548
        """Call function to filter objects by their names.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after filtering, 'gt_bboxes_3d', 'gt_labels_3d' \
                keys are updated in the result dict.
        """
zhangwenwei's avatar
zhangwenwei committed
549
550
551
552
553
554
555
556
557
        gt_labels_3d = input_dict['gt_labels_3d']
        gt_bboxes_mask = np.array([n in self.labels for n in gt_labels_3d],
                                  dtype=np.bool_)
        input_dict['gt_bboxes_3d'] = input_dict['gt_bboxes_3d'][gt_bboxes_mask]
        input_dict['gt_labels_3d'] = input_dict['gt_labels_3d'][gt_bboxes_mask]

        return input_dict

    def __repr__(self):
558
        """str: Return a string that describes the module."""
zhangwenwei's avatar
zhangwenwei committed
559
560
561
        repr_str = self.__class__.__name__
        repr_str += f'(classes={self.classes})'
        return repr_str
wuyuefeng's avatar
wuyuefeng committed
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587


@PIPELINES.register_module()
class IndoorPointSample(object):
    """Indoor point sample.

    Sampling data to a certain number.

    Args:
        name (str): Name of the dataset.
        num_points (int): Number of points to be sampled.
    """

    def __init__(self, num_points):
        self.num_points = num_points

    def points_random_sampling(self,
                               points,
                               num_samples,
                               replace=None,
                               return_choices=False):
        """Points random sampling.

        Sample points to a certain number.

        Args:
588
            points (np.ndarray): 3D Points.
wuyuefeng's avatar
wuyuefeng committed
589
590
            num_samples (int): Number of samples to be sampled.
            replace (bool): Whether the sample is with or without replacement.
liyinhao's avatar
liyinhao committed
591
592
            Defaults to None.
            return_choices (bool): Whether return choice. Defaults to False.
wuyuefeng's avatar
wuyuefeng committed
593
594

        Returns:
595
596
597
598
            tuple[np.ndarray] | np.ndarray:

                - points (np.ndarray): 3D Points.
                - choices (np.ndarray, optional): The generated random samples.
wuyuefeng's avatar
wuyuefeng committed
599
600
601
602
603
604
605
606
607
608
609
        """
        if replace is None:
            replace = (points.shape[0] < num_samples)
        choices = np.random.choice(
            points.shape[0], num_samples, replace=replace)
        if return_choices:
            return points[choices], choices
        else:
            return points[choices]

    def __call__(self, results):
610
611
612
613
614
615
616
617
618
        """Call function to sample points to in indoor scenes.

        Args:
            input_dict (dict): Result dict from loading pipeline.

        Returns:
            dict: Results after sampling, 'points', 'pts_instance_mask' \
                and 'pts_semantic_mask' keys are updated in the result dict.
        """
wuyuefeng's avatar
wuyuefeng committed
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
        points = results['points']
        points, choices = self.points_random_sampling(
            points, self.num_points, return_choices=True)
        pts_instance_mask = results.get('pts_instance_mask', None)
        pts_semantic_mask = results.get('pts_semantic_mask', None)
        results['points'] = points

        if pts_instance_mask is not None and pts_semantic_mask is not None:
            pts_instance_mask = pts_instance_mask[choices]
            pts_semantic_mask = pts_semantic_mask[choices]
            results['pts_instance_mask'] = pts_instance_mask
            results['pts_semantic_mask'] = pts_semantic_mask

        return results

    def __repr__(self):
635
        """str: Return a string that describes the module."""
wuyuefeng's avatar
wuyuefeng committed
636
637
638
        repr_str = self.__class__.__name__
        repr_str += '(num_points={})'.format(self.num_points)
        return repr_str