EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Att-BEVFusion: An Object Detection Algorithm for Camera and LiDAR Fusion Under BEV Features

Peicheng Shi, Mengru Zhou, Xinlong Dong, Aixi Yang

World Electric Vehicle Journal · 20.11.2024 · 15 (11) · 539

DOI: 10.3390/wevj15110539 ↗

Kurz gefasst

Fachartikel in der Zeitschrift World Electric Vehicle Journal, online erschienen am 20.11.2024. Verfasst von Peicheng Shi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Central Guided Local Science and Technology Special Project–Yangtze River Delta Science and Technology Innovation Community Joint Tackling Program Project, Natural Science Foundation of Anhui Province, Wuhu City “Red Casting Light” Major Science and Technology Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To improve the accuracy of detecting small and long-distance objects while self-driving cars are in motion, in this paper, we propose a 3D object detection method, Att-BEVFusion, which fuses camera and LiDAR data in a bird’s-eye view (BEV). First, the transformation from the camera view to the BEV space is achieved through an implicit supervision-based method, and then the LiDAR BEV feature point cloud is voxelized and converted into BEV features. Then, a channel attention mechanism is introduced to design a BEV feature fusion network to realize the fusion of camera BEV feature space and LiDAR BEV feature space. Finally, regarding the issue of insufficient global reasoning in the BEV fusion features generated by the channel attention mechanism, as well as the challenge of inadequate interaction between features. We further develop a BEV self-attention mechanism to apply global operations on the features. This paper evaluates the effectiveness of the Att-BEVFusion fusion algorithm on the nuScenes dataset, and the results demonstrate that the algorithm achieved 72.0% mean average precision (mAP) and 74.3% nuScenes detection score (NDS), with an advanced detection accuracy of 88.9% and 91.8% for single-item detection of automotive and pedestrian categories, respectively.

Förderung

  • Central Guided Local Science and Technology Special Project–Yangtze River Delta Science and Technology Innovation Community Joint Tackling Program Project
  • Natural Science Foundation of Anhui Province
  • Wuhu City “Red Casting Light” Major Science and Technology Project

Zitieren

APA

Shi, P., Zhou, M., Dong, X., & Yang, A. (2024). Att-BEVFusion: An Object Detection Algorithm for Camera and LiDAR Fusion Under BEV Features. World Electric Vehicle Journal, 15(11), 539. https://doi.org/10.3390/wevj15110539

Vancouver

Shi P, Zhou M, Dong X, Yang A. Att-BEVFusion: An Object Detection Algorithm for Camera and LiDAR Fusion Under BEV Features. World Electric Vehicle Journal. 2024;15(11):539. doi:10.3390/wevj15110539

BibTeX
@article{Shi2024,
  author = {Shi, Peicheng and Zhou, Mengru and Dong, Xinlong and Yang, Aixi},
  title = {Att-BEVFusion: An Object Detection Algorithm for Camera and LiDAR Fusion Under BEV Features},
  journal = {World Electric Vehicle Journal},
  year = {2024},
  volume = {15},
  number = {11},
  pages = {539},
  doi = {10.3390/wevj15110539}
}
Kostenlos starten →