Point Density-Aware Voxels for LiDAR 3D Object Detection

03/10/2022
by   Jordan S. K. Hu, et al.
0

LiDAR has become one of the primary 3D object detection sensors in autonomous driving. However, LiDAR's diverging point pattern with increasing distance results in a non-uniform sampled point cloud ill-suited to discretized volumetric feature extraction. Current methods either rely on voxelized point clouds or use inefficient farthest point sampling to mitigate detrimental effects caused by density variation but largely ignore point density as a feature and its predictable relationship with distance from the LiDAR sensor. Our proposed solution, Point Density-Aware Voxel network (PDV), is an end-to-end two stage LiDAR 3D object detection architecture that is designed to account for these point density variations. PDV efficiently localizes voxel features from the 3D sparse convolution backbone through voxel point centroids. The spatially localized voxel features are then aggregated through a density-aware RoI grid pooling module using kernel density estimation (KDE) and self-attention with point density positional encoding. Finally, we exploit LiDAR's point density to distance relationship to refine our final bounding box confidences. PDV outperforms all state-of-the-art methods on the Waymo Open Dataset and achieves competitive results on the KITTI dataset. We provide a code release for PDV which is available at https://github.com/TRAILab/PDV.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/18/2021

RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation

3D object detection from LiDAR data for autonomous driving has been maki...
research
11/17/2017

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

Accurate detection of objects in 3D point clouds is a central problem in...
research
07/17/2023

Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

Voxel-based methods have achieved state-of-the-art performance for 3D ob...
research
08/13/2023

PV-SSD: A Projection and Voxel-based Double Branch Single-Stage 3D Object Detector

LIDAR-based 3D object detection and classification is crucial for autono...
research
03/29/2021

LiDAR R-CNN: An Efficient and Universal 3D Object Detector

LiDAR-based 3D detection in point cloud is essential in the perception s...
research
03/04/2023

Virtual Sparse Convolution for Multimodal 3D Object Detection

Recently, virtual/pseudo-point-based 3D object detection that seamlessly...
research
09/06/2021

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

We present a flexible and high-performance framework, named Pyramid R-CN...

Please sign up or login with your details

Forgot password? Click here to reset