EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Radar–Camera Fusion in Perspective View and Bird’s Eye View for 3D Object Detection

Yuhao Xiao iD, Xiaoqing Chen, Yingkai Wang, Zhongliang Fu

Sensors · 03.10.2025 · 25 (19) · 6106

DOI: 10.3390/s25196106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.10.2025. Verfasst von Yuhao Xiao und 3 weiteren Autor:innen. Beteiligte Einrichtung: Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610213, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Bureau of Chengdu Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Three-dimensional object detection based on the fusion of millimeter-wave radar and cameras is increasingly gaining attention due to characteristics of low cost, high accuracy, and strong robustness. Recently, the bird’s eye view (BEV) fusion paradigm has dominated radar–camera fusion-based 3D object detection methods. In the BEV fusion paradigm, the detection accuracy is jointly determined by the precision of both image BEV features and radar BEV features. The precision of image BEV features is significantly influenced by depth estimation accuracy, whereas estimating depth from a monocular image is naturally a challenging, ill-posed problem. In this article, we propose a novel approach to enhance depth estimation accuracy by fusing camera perspective view (PV) features and radar perspective view features, thereby improving the precision of image BEV features. The refined image BEV features are then fused with radar BEV features to achieve more accurate 3D object detection results. To realize PV fusion, we designed a radar image generation module based on radar cross-section (RCS) and depth information, accurately projecting radar data into the camera view to generate radar images. The radar images are used to extract radar PV features. We present a cross-modal feature fusion module using the attention mechanism to dynamically fuse radar PV features with camera PV features. Comprehensive evaluations on the nuScenes 3D object detection dataset demonstrate that the proposed dual-view fusion paradigm outperforms the BEV fusion paradigm, achieving state-of-the-art performance with 64.2 NDS and 56.3 mAP.

Schlagwörter

Stichwörter der Autor:innen

3D object detectionautonomous vehiclemillimeter-wave radarmulti-view camerassensor fusion

Autor:innen und Institutionen

  • Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610213, China.
  • The School of Computer Science and Technology, University of Chinese Academic of Sciences, Beijing 101408, China.

ORCID-Profile: Yuhao Xiao

Förderung

  • The Bureau of Chengdu Science and Technology

Zitieren

APA

Xiao, Y., Chen, X., Wang, Y., & Fu, Z. (2025). Radar–Camera Fusion in Perspective View and Bird’s Eye View for 3D Object Detection. Sensors, 25(19), 6106. https://doi.org/10.3390/s25196106

Vancouver

Xiao Y, Chen X, Wang Y, Fu Z. Radar–Camera Fusion in Perspective View and Bird’s Eye View for 3D Object Detection. Sensors. 2025;25(19):6106. doi:10.3390/s25196106

BibTeX
@article{Xiao2025,
  author = {Xiao, Yuhao and Chen, Xiaoqing and Wang, Yingkai and Fu, Zhongliang},
  title = {Radar–Camera Fusion in Perspective View and Bird’s Eye View for 3D Object Detection},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {19},
  pages = {6106},
  doi = {10.3390/s25196106}
}
Kostenlos starten →