EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TriQuery-BEV: Enhancing 3D Perception for Autonomous Driving with Temporal Query Filtering and Uncertainty-Aware Fusion

Junyi Dong, Xuemei Chen, Zemin Liu

Sensors · 07.05.2026 · 26 (10) · 2934

DOI: 10.3390/s26102934 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.05.2026. Verfasst von Junyi Dong und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Beijing Institute of Technology, 5 South Zhongguancun Street, Haidian District, Beijing 100811, China. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing BEV perception methods unify multi-view information in a bird’s-eye-view coordinate system, yet their performance in dynamic traffic scenes remains limited by three major error sources: depth-noise amplification during image-to-BEV lifting, representation discontinuity caused by time-varying occlusion and visibility, and temporal drift induced by recursive fusion of historical BEV features. To address these issues while preserving computational tractability, we propose TriQuery-BEV, a modular enhancement framework over BEVFormer that improves BEV query modeling from the perspectives of geometric ambiguity, occlusion robustness, and temporal consistency. The proposed framework integrates three components: Query Mask (QM) for structured regularization in the BEV query space, depth-modulated hybrid positional encoding (DM-HPE) for geometry-aware positional representation, and a Temporal Query Filter (TQF) for uncertainty-aware temporal fusion. Experiments on the nuScenes benchmark demonstrate consistent improvements over BEVFormer across different model scales. TriQuery-BEV improves the nuScenes detection score (NDS) and mean average precision (mAP) by 5.4%/6.4% under the Tiny (ResNet-50) setting and by 6.0%/6.5% under the Base (ResNet-101) setting. It also reduces key true-positive error metrics, including mean translation error (mATE) by 2.9%/6.5%, mean orientation error (mAOE) by 5.7%/8.3%, and mean velocity error (mAVE) by 7.3%/15.0% for Tiny/Base, respectively. Extensive ablations further verify the effectiveness of DM-HPE, TQF, and QM, confirming improved robustness, geometric accuracy, and temporal consistency in highly dynamic environments.

Schlagwörter

Stichwörter der Autor:innen

3D perceptionbird’s-eye view perceptiontemporal query fusion

Autor:innen und Institutionen

  • School of Mechanical Engineering, Beijing Institute of Technology, 5 South Zhongguancun Street, Haidian District, Beijing 100811, China.

Zitieren

APA

Dong, J., Chen, X., & Liu, Z. (2026). TriQuery-BEV: Enhancing 3D Perception for Autonomous Driving with Temporal Query Filtering and Uncertainty-Aware Fusion. Sensors, 26(10), 2934. https://doi.org/10.3390/s26102934

Vancouver

Dong J, Chen X, Liu Z. TriQuery-BEV: Enhancing 3D Perception for Autonomous Driving with Temporal Query Filtering and Uncertainty-Aware Fusion. Sensors. 2026;26(10):2934. doi:10.3390/s26102934

BibTeX
@article{Dong2026,
  author = {Dong, Junyi and Chen, Xuemei and Liu, Zemin},
  title = {TriQuery-BEV: Enhancing 3D Perception for Autonomous Driving with Temporal Query Filtering and Uncertainty-Aware Fusion},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {2934},
  doi = {10.3390/s26102934}
}
Kostenlos starten →