EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SpecBEV: An End-to-End BEV 3D Object Detection Algorithm Based on Frequency-Domain Analysis and Geometric Alignment

Yu Lin, Shijie Jia iD

Sensors · 03.06.2026 · 26 (11) · 3551

DOI: 10.3390/s26113551 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.06.2026. Verfasst von Yu Lin und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering, Dalian Jiaotong University, Dalian 116028, China. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes SpecBEV, an enhanced multi-view 3D object detection framework for autonomous driving using bird’s-eye-view (BEV) representations. Compared with LiDAR-based methods, multi-camera perception offers higher cost-effectiveness and flexibility. However, existing end-to-end BEV detectors suffer from illumination variations, occlusions, and cross-view inconsistencies during feature projection and fusion. These issues often introduce redundant background activations and geometric misalignment in the BEV space, leading to missed detections, false positives, and unstable localization. To address them, we introduce a frequency-prior spatial attention module (SA-Freq). It utilizes fixed discrete cosine transform (DCT) bases to model the multi-band responses of BEV features and produce spatial attention weights that suppress redundant activations and enhance target-related regions. We further design a cross-view feature alignment module (CFA) to ensure consistency between single-view BEV features and the fused BEV representation, thereby reducing geometric inconsistency and improving localization stability. Experiments on the nuScenes validation set demonstrate that SpecBEV achieves 0.3856 in mAP and 0.4871 in NDS. Compared with the BEVDet baseline, it yields an absolute gain of 0.1028 (36.35% relative improvement) in mAP and an absolute gain of 0.1371 (39.17% relative improvement) in NDS, which validates the effectiveness of the proposed method.

Schlagwörter

Stichwörter der Autor:innen

BEV object detectioncross-view feature alignmentfrequency priormulti-view fusionspatial attention

Autor:innen und Institutionen

  • School of Electrical Engineering, Dalian Jiaotong University, Dalian 116028, China.

ORCID-Profile: Shijie Jia

Zitieren

APA

Lin, Y., & Jia, S. (2026). SpecBEV: An End-to-End BEV 3D Object Detection Algorithm Based on Frequency-Domain Analysis and Geometric Alignment. Sensors, 26(11), 3551. https://doi.org/10.3390/s26113551

Vancouver

Lin Y, Jia S. SpecBEV: An End-to-End BEV 3D Object Detection Algorithm Based on Frequency-Domain Analysis and Geometric Alignment. Sensors. 2026;26(11):3551. doi:10.3390/s26113551

BibTeX
@article{Lin2026,
  author = {Lin, Yu and Jia, Shijie},
  title = {SpecBEV: An End-to-End BEV 3D Object Detection Algorithm Based on Frequency-Domain Analysis and Geometric Alignment},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3551},
  doi = {10.3390/s26113551}
}
Kostenlos starten →