EUVIMEDEUVIMED entdecken
Crossref

OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction

Zhenxing Ming, Julie Stephany Berrio, Mao Shan, Stewart Worrall

IEEE Transactions on Intelligent Vehicles · 2025-05 · 10 (5) · 3421-3433

DOI: 10.1109/tiv.2024.3453293 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Vehicles, 2025-05. Verfasst von Zhenxing Ming und 3 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: Australian Centre for Robotics.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A comprehensive understanding of 3D scenes is crucial in autonomous vehicles (AVs), and recent models for 3D semantic occupancy prediction have successfully addressed the challenge of describing real-world objects with varied shapes and classes. However, existing methods for 3D semantic occupancy prediction heavily rely on surround-view camera images, making them susceptible to changes in lighting and weather conditions. This paper introduces OccFusion, a novel sensor fusion framework for predicting 3D semantic occupancy. By integrating features from additional sensors, such as lidar and surround view radars, our framework enhances the accuracy and robustness of occupancy prediction, resulting in top-tier performance on the nuScenes benchmark. Furthermore, extensive experiments conducted on the nuScenes and semanticKITTI dataset, including challenging night and rainy scenarios, confirm the superior performance of our sensor fusion strategy across various perception ranges.

Förderung

  • Australian Centre for Robotics

Zitieren

APA

Ming, Z., Berrio, J. S., Shan, M., & Worrall, S. (2025). OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction. IEEE Transactions on Intelligent Vehicles, 10(5), 3421-3433. https://doi.org/10.1109/tiv.2024.3453293

Vancouver

Ming Z, Berrio JS, Shan M, Worrall S. OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction. IEEE Transactions on Intelligent Vehicles. 2025;10(5):3421-3433. doi:10.1109/tiv.2024.3453293

BibTeX
@article{Ming2025,
  author = {Ming, Zhenxing and Berrio, Julie Stephany and Shan, Mao and Worrall, Stewart},
  title = {OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction},
  journal = {IEEE Transactions on Intelligent Vehicles},
  year = {2025},
  volume = {10},
  number = {5},
  pages = {3421--3433},
  doi = {10.1109/tiv.2024.3453293}
}
Kostenlos starten →