Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds

Abstract

Object detection in point cloud data is one of the key components in computer vision systems, especially for autonomous driving applications. In this work, we present Voxel-FPN, a novel one-stage 3D object detector that utilizes raw data from LIDAR sensors only. The core framework consists of an encoder network and a corresponding decoder followed by a region proposal network. Encoder extracts multi-scale voxel information in a bottom-up manner while decoder fuses multiple feature maps from various scales in a top-down way. Extensive experiments show that the proposed method has better performance on extracting features from point data and demonstrates its superiority over some baselines on the challenging KITTI-3D benchmark, obtaining good performance on both speed and accuracy in real-world scenarios.

References in corpus (4)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• 3D Fully Convolutional Network for Vehicle Detection in Point Cloud

Cited by in corpus (9)

• 3D Object Detection for Autonomous Driving: A Survey
• PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
• HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
• Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
• OCM3D: Object-Centric Monocular 3D Object Detection
• PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module
• LiDAR R-CNN: An Efficient and Universal 3D Object Detector