bevfusion 学习笔记

目录

tensorrt ros部署：

也依赖ros2 c++

ros2安装指导：

相机标定工具源码：

官方github，部分模型开源

---

tensorrt ros部署：

https://github.com/linClubs/BEVFusion-ROS-TensorRT

也依赖ros2 c++

GitHub - newintelligence4/BEVfusion_preprocess: Multiple Lidar preprocessor for BEVfusion

ros2安装指导：

ROS2学习笔记（一）——Win11安装及使用 - 知乎

安装手册：?

Windows (binary) — ROS 2 Documentation: Humble documentation

下载地址：Releases · ros2/ros2 · GitHub

相机标定工具源码：

GitHub - linClubs/Calibration-Is-All-You-Need: calibration is you need including camera、imu、camera2camera、 camera2lidar、imu2camera、imu2lidar.

官方github，部分模型开源

https://github.com/ADLab-AutoDrive/BEVFusion

没有开源centerpoint版，

Main Results

nuScenes detection test

Model	Head	3DBackbone	2DBackbone	mAP	NDS	Link
BEVFusion	TransFusion-L	VoxelNet	Dual-Swin-T	69.2	71.8	Detection
BEVFusion*	TransFusion-L	VoxelNet	Dual-Swin-T	71.3	73.3	Leadboard

nuScenes detection validation

Model	Head	3DBackbone	2DBackbone	mAP	NDS	Model
BEVFusion	PointPillars	-	Dual-Swin-T	22.9	31.1	Model
BEVFusion	PointPillars	PointPillars	-	35.1	49.8	Model
BEVFusion	PointPillars	PointPillars	Dual-Swin-T	53.5	60.4	Model
BEVFusion	CenterPoint	-	Dual-Swin-T	27.1	32.1	-
BEVFusion	CenterPoint	VoxelNet	-	57.1	65.4	-
BEVFusion	CenterPoint	VoxelNet	Dual-Swin-T	64.2	68.0	-
BEVFusion	TransFusion-L	-	Dual-Swin-T	22.7	26.1	-
BEVFusion	TransFusion-L	VoxelNet	-	64.9	69.9	-
BEVFusion	TransFusion-L	VoxelNet	Dual-Swin-T	67.9	71.0	-
BEVFusion*	TransFusion-L	VoxelNet	Dual-Swin-T	69.6	72.1	Model

GitHub - mit-han-lab/bevfusion: [ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

3D Object Detection (on nuScenes validation)

Model	Modality	mAP	NDS	Checkpoint
BEVFusion	C+L	68.52	71.38	Link
Camera-Only Baseline	C	35.56	41.21	Link
LiDAR-Only Baseline	L	64.68	69.28	Link

Note: The camera-only object detection baseline is a variant of BEVDet-Tiny with a much heavier view transformer and other differences in hyperparameters. Thanks to our?efficient BEV pooling?operator, this model runs fast and has higher mAP than BEVDet-Tiny under the same input resolution. Please refer to?BEVDet repo?for the original BEVDet-Tiny implementation. The LiDAR-only baseline is TransFusion-L.

BEV Map Segmentation (on nuScenes validation)

Model	Modality	mIoU	Checkpoint
BEVFusion	C+L	62.95	Link
Camera-Only Baseline	C	57.09	Link
LiDAR-Only Baseline	L	48.56	Link