Skip to main navigation Skip to search Skip to main content

3D Vehicle Detection Using Multi-Level Fusion From Point Clouds and Images

  • Kun Zhao
  • , Lingfei Ma
  • , Yu Meng
  • , Li Liu*
  • , Junbo Wang
  • , Jose Marcato Junior
  • , Wesley Nunes Goncalves
  • , Jonathan Li*
  • *Corresponding author for this work
  • University of Waterloo
  • Central University of Finance and Economics
  • University of Science and Technology Beijing
  • Xiamen University
  • Universidade Federal de Mato Grosso do Sul

Research output: Contribution to journal › Article › peer-review

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.

Original languageEnglish
Pages (from-to)15146-15154
Number of pages9
JournalIEEE Transactions on Intelligent Transportation Systems
Volume23
Issue number9
DOIs
StatePublished - 1 Sep 2022
Externally publishedYes

Keywords

  • 3D vehicle detection
  • autonomous driving
  • data fusion
  • deep learning
  • false detection
  • point cloud processing

Fingerprint

Dive into the research topics of '3D Vehicle Detection Using Multi-Level Fusion From Point Clouds and Images'. Together they form a unique fingerprint.

Cite this