HPV-RCNN: Hybrid Point–Voxel Two-Stage Network for LiDAR-Based 3-D Object Detection
- 10 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 10 (6) , 3066-3076
Abstract
The current two-stage detectors remarkably benefit from hybrid representation of points and 3-D voxels, but they have high time cost and leave room for improving the accuracy of small objects. On the contrary, 2-D voxel-based methods tend to have good efficiency and better performance for small objects. An intuitive idea of optimizing a two-stage algorithm is to use a 2-D voxel-based backbone. However, naive representation substitution cannot achieve optimal joint learning of each representation and may cause a decrease in accuracy. In this article, we propose hybrid point–voxel RCNN (HPV-RCNN), a novel point cloud detection network which combines the merits of points and 2-D voxels. First, we propose a multiattentive voxel feature encoding module (MAVFE) to exploit multilevel attention of multiscale voxels. We also present a partial fusion pyramid network (PFPN) to effectively integrate multiresolution features and generate high-quality proposals. Then, a multiscale region of interest (RoI)-grid pooling (MSRGP) module is proposed to adaptively abstract proposal-specific features from sampled keypoints in multiple receptive fields. In addition, a cascade attentive module (CAM) is adopted to achieve incrementally proposal refinement by subsequent multiple subnetworks. Our method reaches top performance among two-stage methods in Cyclist and Pedestrian categories on the KITTI dataset while achieving real-time inference speed. Extensive experiments on challenging roadside DAIR-V2X-I dataset also demonstrate that our method achieves superior detection performance.Keywords
Funding Information
- National Natural Science Foundation of China (62071049)
- Natural Science Foundation of Beijing Municipality (4222018)
- Key Research Project of China Telecom Research Institute
This publication has 34 references indexed in Scilit:
- SECOND: Sparsely Embedded Convolutional DetectionSensors, 2018
- Joint 3D Proposal Generation and Object Detection from View Aggregation2018
- Frustum PointNets for 3D Object Detection from RGB-D Data2018
- Path Aggregation Network for Instance Segmentation2018
- Cascade R-CNN: Delving Into High Quality Object Detection2018
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection2018
- Focal Loss for Dense Object Detection2017
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- Multi-view 3D Object Detection Network for Autonomous Driving2017
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012