01 前言：
3D目标检测是计算机视觉领域中一个重要的任务，广泛应用于自动驾驶、机器人导航、无人机等领域。由于3D数据的复杂性和多样性，数据预处理在3D目标检测中扮演着关键角色。良好的预处理策略不仅可以提升模型的检测精度，还可以显著提高模型的训练和推理效率。本文将探讨几种常用的3D目标检测预处理优化策略。
02 对原始数据进行编码
使用强度信息与时间信息
def absolute_coordinates_encoding(self, points=None):if points is None:num_output_features = len(self.used_feature_list)return num_output_featuresassert points.shape[-1] == len(self.src_feature_list)point_feature_list = [points[:, 0:3]]for x in self.used_feature_list:if x in ['x', 'y', 'z']:continueidx = self.src_feature_list.index(x)point_feature_list.append(points[:, idx:idx+1])point_features = np.concatenate(point_feature_list, axis=1)return point_features, True使用多帧数据
def get_lidar_with_sweeps(self, index, max_sweeps=1):info = self.infos[index]lidar_path = self.root_path / info['lidar_path']points = np.fromfile(str(lidar_path), dtype=np.float32, count=-1).reshape([-1, 5])[:, :4] sweep_points_list = [points]sweep_times_list = [np.zeros((points.shape[0], 1))]for k in np.random.choice(len(info['sweeps']), max_sweeps - 1, replace=False):points_sweep, times_sweep = self.get_sweep(info['sweeps'][k])sweep_points_list.append(points_sweep)sweep_times_list.append(times_sweep)points = np.concatenate(sweep_points_list, axis=0)times = np.concatenate(sweep_times_list, axis=0).astype(points.dtype)points = np.concatenate((points, times), axis=1)return points03 对原始数据进行处理
打乱数据
def shuffle_points(self, data_dict=None, config=None):if data_dict is None:return partial(self.shuffle_points, config=config)if config.SHUFFLE_ENABLED[self.mode]:points = data_dict['points']shuffle_idx = np.random.permutation(points.shape[0])points = points[shuffle_idx]data_dict['points'] = pointsreturn data_dict进行翻转
def double_flip(self, points):# y flippoints_yflip = points.copy()points_yflip[:, 1] = -points_yflip[:, 1]# x flippoints_xflip = points.copy()points_xflip[:, 0] = -points_xflip[:, 0]# x y flippoints_xyflip = points.copy()points_xyflip[:, 0] = -points_xyflip[:, 0]points_xyflip[:, 1] = -points_xyflip[:, 1]return points_yflip, points_xflip, points_xyflip将其转成voxel
def transform_points_to_voxels(self, data_dict=None, config=None):if data_dict is None:grid_size = (self.point_cloud_range[3:6] - self.point_cloud_range[0:3]) / np.array(config.VOXEL_SIZE)self.grid_size = np.round(grid_size).astype(np.int64)self.voxel_size = config.VOXEL_SIZE# just bind the config, we will create the VoxelGeneratorWrapper later,# to avoid pickling issues in multiprocess spawnreturn partial(self.transform_points_to_voxels, config=config)if self.voxel_generator is None:self.voxel_generator = VoxelGeneratorWrapper(vsize_xyz=config.VOXEL_SIZE,coors_range_xyz=self.point_cloud_range,num_point_features=self.num_point_features,max_num_points_per_voxel=config.MAX_POINTS_PER_VOXEL,max_num_voxels=config.MAX_NUMBER_OF_VOXELS[self.mode],)points = data_dict['points']voxel_output = self.voxel_generator.generate(points)voxels, coordinates, num_points = voxel_output对数据进行下采样
def sample_points(self, data_dict=None, config=None):if data_dict is None:return partial(self.sample_points, config=config)num_points = config.NUM_POINTS[self.mode]if num_points == -1:return data_dictpoints = data_dict['points']if num_points < len(points):pts_depth = np.linalg.norm(points[:, 0:3], axis=1)pts_near_flag = pts_depth < 40.0far_idxs_choice = np.where(pts_near_flag == 0)[0]near_idxs = np.where(pts_near_flag == 1)[0]choice = []if num_points > len(far_idxs_choice):near_idxs_choice = np.random.choice(near_idxs, num_points - 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_choiceelse: choice = np.arange(0, len(points), dtype=np.int32)choice = np.random.choice(choice, num_points, replace=False)np.random.shuffle(choice)else:choice = np.arange(0, len(points), dtype=np.int32)if num_points > len(points):extra_choice = np.random.choice(choice, num_points - len(points), replace=False)choice = np.concatenate((choice, extra_choice), axis=0)np.random.shuffle(choice)data_dict['points'] = points[choice]return data_dict04 对真值数据进行处理
将数据翻转
def random_world_flip(self, data_dict=None, config=None):if data_dict is None:return partial(self.random_world_flip, config=config)gt_boxes, points = data_dict['gt_boxes'], data_dict['points']for cur_axis in config['ALONG_AXIS_LIST']:assert cur_axis in ['x', 'y']gt_boxes, points, enable = getattr(augmentor_utils, 'random_flip_along_%s' % cur_axis)(gt_boxes, points, return_flip=True)data_dict['flip_%s'%cur_axis] = enableif 'roi_boxes' in data_dict.keys():num_frame, num_rois,dim = data_dict['roi_boxes'].shaperoi_boxes, _, _ = getattr(augmentor_utils, 'random_flip_along_%s' % cur_axis)(data_dict['roi_boxes'].reshape(-1,dim), np.zeros([1,3]), return_flip=True, enable=enable)data_dict['roi_boxes'] = roi_boxes.reshape(num_frame, num_rois,dim)data_dict['gt_boxes'] = gt_boxesdata_dict['points'] = pointsreturn data_dict
将数据旋转
def random_world_rotation(self, data_dict=None, config=None):if data_dict is None:return partial(self.random_world_rotation, config=config)rot_range = config['WORLD_ROT_ANGLE']if not isinstance(rot_range, list):rot_range = [-rot_range, rot_range]gt_boxes, points, noise_rot = augmentor_utils.global_rotation(data_dict['gt_boxes'], data_dict['points'], rot_range=rot_range, return_rot=True)if 'roi_boxes' in data_dict.keys():num_frame, num_rois,dim = data_dict['roi_boxes'].shaperoi_boxes, _, _ = augmentor_utils.global_rotation(data_dict['roi_boxes'].reshape(-1, dim), np.zeros([1, 3]), rot_range=rot_range, return_rot=True, noise_rotation=noise_rot)data_dict['roi_boxes'] = roi_boxes.reshape(num_frame, num_rois,dim)data_dict['gt_boxes'] = gt_boxesdata_dict['points'] = pointsdata_dict['noise_rot'] = noise_rotreturn data_dict将数据缩放
def random_world_scaling(self, data_dict=None, config=None):if data_dict is None:return partial(self.random_world_scaling, config=config)if 'roi_boxes' in data_dict.keys():gt_boxes, roi_boxes, points, noise_scale = augmentor_utils.global_scaling_with_roi_boxes(data_dict['gt_boxes'], data_dict['roi_boxes'], data_dict['points'], config['WORLD_SCALE_RANGE'], return_scale=True)data_dict['roi_boxes'] = roi_boxeselse:gt_boxes, points, noise_scale = augmentor_utils.global_scaling(data_dict['gt_boxes'], data_dict['points'], config['WORLD_SCALE_RANGE'], return_scale=True)data_dict['gt_boxes'] = gt_boxesdata_dict['points'] = pointsdata_dict['noise_scale'] = noise_scalereturn data_dict你还知道哪些预处理的方法，留下你的想法？
最后别忘了，帮忙点“在看”。
您的点赞，在看，是我创作的动力。
关注我的公众号auto_driver_ai(Ai fighting), 第一时间获取更新内容。
AiFighing是全网第一且唯一以代码、项目的形式讲解自动驾驶感知方向的关键技术，关注我，一起学习自动驾驶感知技术。
)
