3D Vehicle Detection Using Multi-Level Fusion From Point Clouds and Images
- 11 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (9) , 15146-15154
Abstract
3D vehicle detectors based on point clouds generally have higher detection performance than detectors based on multi-sensors. However, with the lack of texture information, point-based methods get many missing detection of occluded and distant vehicles, and false detection with high-confidence of similarly shaped objects, which is a potential threat to traffic safety. Therefore, in the long run, fusion-based methods have more potential. This paper presents a multi-level fusion network for 3D vehicle detection from point clouds and images. The fusion network includes three stages: data-level fusion of point clouds and images, feature-level fusion of voxel and Bird’s Eye View (BEV) in the point cloud branch, and feature-level fusion of point clouds and images. Besides, a novel coarse-fine detection header is proposed, which simulates the two-stage detectors, generating coarse proposals on the encoder, and refining them on the decoder. Extensive experiments show that the proposed network has better detection performance on occluded and distant vehicles, and reduces the false detection of similarly shaped objects, proving its superiority over some state-of-the-art detectors on the challenging KITTI benchmark. Ablation studies have also demonstrated the effectiveness of each designed module.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFE0192900)
- National Natural Science Foundation of China (41871380, 42101451)
This publication has 33 references indexed in Scilit:
- Vehicle detection and localization on bird's eye view elevation images using convolutional neural network2017
- Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks2017
- A Low-Complexity Scheme for Partially Occluded Pedestrian Detection Using LIDAR-RADAR Sensor Fusion2016
- Vehicle Detection from 3D Lidar Using Fully Convolutional Network2016
- Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- Voting for Voting in Online Point Cloud Object Detection2015
- Fully convolutional networks for semantic segmentation2015
- Sliding Shapes for 3D Object Detection in Depth Images2014