pointpillars

PointPillars detection models.

First page of PointPillars: Fast Encoders for Object Detection from Point Clouds

1812.05784 · December 2018

Classes:

PillarFeatureNet –

Pillar feature encoder (PillarVFE).
PointPillarsDetection –

PointPillars 3D object detector (packed point format).
PointPillarsMultiHeadDetection –

PointPillars with a multi-group anchor head (nuScenes 10-class, packed point format).

Functions:

scatter_to_bev –

Scatter pillar features back to a dense BEV pseudo-image.

PillarFeatureNet [source] ¶

PillarFeatureNet(
    in_channels: int,
    feat_channels: Sequence[int],
    voxel_size: Sequence[float],
    point_cloud_range: Sequence[float],
    *,
    act: Union[str, Callable, None] = "relu",
    act_kwargs: Optional[Dict[str, Any]] = None,
    norm: Union[str, Callable, None] = "batch_norm",
    norm_kwargs: Optional[Dict[str, Any]] = None,
)

Bases: Module

Pillar feature encoder (PillarVFE).

Augments each point in a pillar with its offset to the pillar's point-cluster mean and to the pillar center, then applies a stack of PillarFeatureLayers.

Parameters:

in_channels (int) –

Raw point feature channels (e.g. \(4\) for \(x, y, z, \text{intensity}\)).
feat_channels (Sequence[int]) –

Output channels of each pillar feature-net layer.
voxel_size (Sequence[float]) –

Pillar size \((v_x, v_y, v_z)\).
point_cloud_range (Sequence[float]) –

Range \((x_\min, y_\min, z_\min, x_\max, y_\max, z_\max)\).
act (Union[str, Callable, None], default: 'relu' ) –

Activation type or callable.
act_kwargs (Optional[Dict[str, Any]], default: None ) –

Extra activation arguments.
norm (Union[str, Callable, None], default: 'batch_norm' ) –

Normalization type or callable.
norm_kwargs (Optional[Dict[str, Any]], default: None ) –

Extra normalization arguments.

PointPillarsDetection [source] ¶

PointPillarsDetection(
    in_channels: int = 4,
    num_classes: int = 3,
    *,
    voxel_size: Sequence[float] = (0.16, 0.16, 4.0),
    point_cloud_range: Sequence[float] = (
        0.0,
        -39.68,
        -3.0,
        69.12,
        39.68,
        1.0,
    ),
    anchor_sizes: Sequence[Sequence[float]],
    anchor_bottom_heights: Sequence[float],
    feature_map_stride: int,
    anchor_rotations: Sequence[float] = (0.0, 1.57),
    feat_channels: Sequence[int] = (64,),
    layer_nums: Sequence[int] = (3, 5, 5),
    layer_strides: Sequence[int] = (2, 2, 2),
    num_filters: Sequence[int] = (64, 128, 256),
    upsample_strides: Sequence[int] = (1, 2, 4),
    num_upsample_filters: Sequence[int] = (128, 128, 128),
    num_dir_bins: int = 2,
    dir_offset: float = 0.78539,
    dir_limit_offset: float = 0.0,
    act: Union[str, Callable, None] = "relu",
    act_kwargs: Optional[Dict[str, Any]] = None,
    norm: Union[str, Callable, None] = "batch_norm",
    norm_kwargs: Optional[Dict[str, Any]] = None,
)

Bases: DetectionModel

PointPillars 3D object detector (packed point format).

Reference: PointPillars: Fast Encoders for Object Detection from Point Clouds (Lang et al., 2019). Reference implementation: open-mmlab/OpenPCDet.

Parameters:

in_channels (int, default: 4 ) –

Raw point feature channels including xyz (e.g. \(4\) for \(x, y, z, \text{intensity}\)).
num_classes (int, default: 3 ) –

Number of foreground classes.
voxel_size (Sequence[float], default: (0.16, 0.16, 4.0) ) –

Pillar size \((v_x, v_y, v_z)\).
point_cloud_range (Sequence[float], default: (0.0, -39.68, -3.0, 69.12, 39.68, 1.0) ) –

Range \((x_\min, y_\min, z_\min, x_\max, y_\max, z_\max)\).
anchor_sizes (Sequence[Sequence[float]]) –

Per-class box size \((d_x, d_y, d_z)\), one row per class.
anchor_bottom_heights (Sequence[float]) –

Per-class anchor bottom \(z\), one per class.
anchor_rotations (Sequence[float], default: (0.0, 1.57) ) –

Yaw angles (radians) shared by all classes.
feature_map_stride (int) –

BEV feature-map stride of the head.
feat_channels (Sequence[int], default: (64,) ) –

Output channels of the pillar feature net.
layer_nums (Sequence[int], default: (3, 5, 5) ) –

2D backbone conv counts per level.
layer_strides (Sequence[int], default: (2, 2, 2) ) –

2D backbone downsample strides per level.
num_filters (Sequence[int], default: (64, 128, 256) ) –

2D backbone channel widths per level.
upsample_strides (Sequence[int], default: (1, 2, 4) ) –

2D backbone upsample strides per level.
num_upsample_filters (Sequence[int], default: (128, 128, 128) ) –

2D backbone upsample channels per level.
num_dir_bins (int, default: 2 ) –

Number of direction bins in the head.
dir_offset (float, default: 0.78539 ) –

Direction-classifier angle offset.
dir_limit_offset (float, default: 0.0 ) –

Heading wrap offset used during decoding.
act (Union[str, Callable, None], default: 'relu' ) –

Activation type or callable for the pillar feature net and 2D backbone.
act_kwargs (Optional[Dict[str, Any]], default: None ) –

Extra activation arguments.
norm (Union[str, Callable, None], default: 'batch_norm' ) –

Normalization type or callable for the pillar feature net and 2D backbone.
norm_kwargs (Optional[Dict[str, Any]], default: None ) –

Extra normalization arguments.

Methods:

configure_vfe –

Build the pillar feature net.
configure_backbone –

Build the 2D BEV backbone.
configure_head –

Build the single-group anchor head.
decode –

Decode a forward output into raw per-anchor detections (see AnchorHead.decode).
reset_classifier –

Replace the classification branch of the detection head for num_classes outputs.

Attributes:

num_features (int) –

Channel count \(C\) of the BEV feature map entering the head.

num_features `property` ¶

num_features: int

Channel count \(C\) of the BEV feature map entering the head.

configure_vfe [source] ¶

configure_vfe() -> PillarFeatureNet

Build the pillar feature net.

configure_backbone [source] ¶

configure_backbone() -> BEVBackbone

Build the 2D BEV backbone.

configure_head [source] ¶

configure_head() -> AnchorHead

Build the single-group anchor head.

decode [source] ¶

decode(out: AnchorHeadOutput) -> Detection3D

Decode a forward output into raw per-anchor detections (see AnchorHead.decode).

reset_classifier [source] ¶

reset_classifier(num_classes: int) -> None

Replace the classification branch of the detection head for num_classes outputs.

Models whose head is not rebuildable in isolation raise NotImplementedError.

PointPillarsMultiHeadDetection [source] ¶

PointPillarsMultiHeadDetection(
    in_channels: int = 5,
    num_classes: int = 10,
    *,
    voxel_size: Sequence[float] = (0.2, 0.2, 8.0),
    point_cloud_range: Sequence[float] = (
        -51.2,
        -51.2,
        -5.0,
        51.2,
        51.2,
        3.0,
    ),
    anchor_sizes: Sequence[Sequence[float]],
    anchor_bottom_heights: Sequence[float],
    head_class_groups: Sequence[Sequence[int]],
    feature_map_stride: int,
    anchor_rotations: Sequence[float] = (0.0, 1.57),
    feat_channels: Sequence[int] = (64,),
    layer_nums: Sequence[int] = (3, 5, 5),
    layer_strides: Sequence[int] = (2, 2, 2),
    num_filters: Sequence[int] = (64, 128, 256),
    upsample_strides: Sequence[float] = (0.5, 1, 2),
    num_upsample_filters: Sequence[int] = (128, 128, 128),
    shared_conv_num_filter: int = 64,
    act: Union[str, Callable, None] = "relu",
    act_kwargs: Optional[Dict[str, Any]] = None,
    norm: Union[str, Callable, None] = "batch_norm",
    norm_kwargs: Optional[Dict[str, Any]] = None,
)

Bases: DetectionModel

PointPillars with a multi-group anchor head (nuScenes 10-class, packed point format).

Reference implementation: open-mmlab/OpenPCDet (cbgs_pp_multihead). Same pillar trunk as PointPillarsDetection but with an MultiGroupAnchorHead head (per-group heads, sincos + velocity box code). Input points carry 5 features (\(x, y, z, \text{intensity}, \Delta t\) from 10-sweep aggregation).

Parameters:

in_channels (int, default: 5 ) –

Raw point feature channels including xyz (5 for nuScenes).
num_classes (int, default: 10 ) –

Number of foreground classes (10 for nuScenes).
voxel_size (Sequence[float], default: (0.2, 0.2, 8.0) ) –

Pillar size \((v_x, v_y, v_z)\).
point_cloud_range (Sequence[float], default: (-51.2, -51.2, -5.0, 51.2, 51.2, 3.0) ) –

Range \((x_\min, y_\min, z_\min, x_\max, y_\max, z_\max)\).
anchor_sizes (Sequence[Sequence[float]]) –

Per-class box size \((d_x, d_y, d_z)\), one row per class.
anchor_bottom_heights (Sequence[float]) –

Per-class anchor bottom \(z\), one per class.
head_class_groups (Sequence[Sequence[int]]) –

Class-index groups, one per RPN head (e.g. [[0], [1, 2], ...]).
anchor_rotations (Sequence[float], default: (0.0, 1.57) ) –

Yaw angles (radians) shared by all classes.
feature_map_stride (int) –

BEV feature-map stride of the head.
feat_channels (Sequence[int], default: (64,) ) –

Pillar feature-net output channels.
layer_nums (Sequence[int], default: (3, 5, 5) ) –

2D backbone conv counts per level.
layer_strides (Sequence[int], default: (2, 2, 2) ) –

2D backbone downsample strides per level.
num_filters (Sequence[int], default: (64, 128, 256) ) –

2D backbone channel widths per level.
upsample_strides (Sequence[float], default: (0.5, 1, 2) ) –

2D backbone upsample factors per level (may be < 1).
num_upsample_filters (Sequence[int], default: (128, 128, 128) ) –

2D backbone upsample channels per level.
shared_conv_num_filter (int, default: 64 ) –

Channels of the head's shared conv.
act (Union[str, Callable, None], default: 'relu' ) –

Activation type or callable for the pillar feature net, 2D backbone and head.
act_kwargs (Optional[Dict[str, Any]], default: None ) –

Extra activation arguments.
norm (Union[str, Callable, None], default: 'batch_norm' ) –

Normalization type or callable for the pillar feature net, 2D backbone and head.
norm_kwargs (Optional[Dict[str, Any]], default: None ) –

Extra normalization arguments.

Methods:

configure_vfe –

Build the pillar feature net.
configure_backbone –

Build the 2D BEV backbone.
configure_head –

Build the multi-group anchor head.
decode –

Decode a forward output into raw per-anchor detections (see MultiGroupAnchorHead.decode).
reset_classifier –

Replace the classification branch of the detection head for num_classes outputs.

Attributes:

num_features (int) –

Channel count \(C\) of the BEV feature map entering the head.

num_features `property` ¶

num_features: int

Channel count \(C\) of the BEV feature map entering the head.

configure_vfe [source] ¶

configure_vfe() -> PillarFeatureNet

Build the pillar feature net.

configure_backbone [source] ¶

configure_backbone() -> BEVBackbone

Build the 2D BEV backbone.

configure_head [source] ¶

configure_head() -> MultiGroupAnchorHead

Build the multi-group anchor head.

decode [source] ¶

decode(out: AnchorHeadMultiOutput) -> Detection3D

Decode a forward output into raw per-anchor detections (see MultiGroupAnchorHead.decode).

reset_classifier [source] ¶

reset_classifier(num_classes: int) -> None

Replace the classification branch of the detection head for num_classes outputs.

Models whose head is not rebuildable in isolation raise NotImplementedError.

scatter_to_bev [source] ¶

scatter_to_bev(
    pillar_features: Tensor,
    voxel_indices: Tensor,
    batch_size: int,
    grid_size: Tuple[int, int, int],
) -> Tensor

Scatter pillar features back to a dense BEV pseudo-image.

Stateless scatter of per-pillar features onto a dense bird's-eye-view canvas indexed by each pillar's \((y, x)\) voxel grid index. The channel count is taken from pillar_features.

Parameters:

pillar_features (Tensor) –

Per-pillar features of shape \((P, C)\).
voxel_indices (Tensor) –

Per-pillar voxel indices of shape \((P, 4)\) with columns \((\text{batch}, z, y, x)\) and \(z = 0\).
batch_size (int) –

Number of samples \(B\) in the batch.
grid_size (Tuple[int, int, int]) –

Voxel grid size \((n_x, n_y, n_z)\) with \(n_z = 1\).

Returns:

Tensor –

Dense BEV pseudo-image of shape \((B, C, n_y, n_x)\).

Shape

Input: \((P, C)\) and \((P, 4)\).
Output: \((B, C, n_y, n_x)\).

Example

import torch
from torch_pointcloud.models.pointpillars import scatter_to_bev

pillar_features = torch.randn(120, 64)
voxel_indices = torch.zeros(120, 4, dtype=torch.long)
voxel_indices[:, 2] = torch.randint(0, 496, (120,))
voxel_indices[:, 3] = torch.randint(0, 432, (120,))
bev = scatter_to_bev(pillar_features, voxel_indices, batch_size=1, grid_size=(432, 496, 1))
print(bev.shape)

pointpillars

PillarFeatureNet [source] ¶

PointPillarsDetection [source] ¶

num_features property ¶

configure_vfe [source] ¶

configure_backbone [source] ¶

configure_head [source] ¶

decode [source] ¶

reset_classifier [source] ¶

PointPillarsMultiHeadDetection [source] ¶

num_features property ¶

configure_vfe [source] ¶

configure_backbone [source] ¶

configure_head [source] ¶

decode [source] ¶

reset_classifier [source] ¶

scatter_to_bev [source] ¶

num_features `property` ¶

num_features `property` ¶