EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

A Survey of Deep Learning-Based 3D Object Detection Methods for Autonomous Driving Across Different Sensor Modalities

Miguel Valverde iD, Alexandra Moutinho iD, João-Vitor Zacchi iD

Sensors · 24.08.2025 · 25 (17) · 5264

DOI: 10.3390/s25175264 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 24.08.2025. Verfasst von Miguel Valverde und 2 weiteren Autor:innen. Beteiligte Einrichtung: Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 263 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação para a Ciência e Tecnologia, Fundação para a Ciência e a Tecnologia (FCT) for its financial support via the project LAETA Base Funding.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a comprehensive survey of deep learning-based methods for 3D object detection in autonomous driving, focusing on their use of diverse sensor modalities, including monocular cameras, stereo vision, LiDAR, radar, and multi-modal fusion. To systematically organize the literature, a structured taxonomy is proposed that categorizes methods by input modality. The review also outlines the chronological evolution of these approaches, highlighting major architectural developments and paradigm shifts. Furthermore, the surveyed methods are quantitatively compared using standard evaluation metrics across benchmark datasets in autonomous driving scenarios. Overall, this work provides a detailed and modality-agnostic overview of the current landscape of deep learning approaches for 3D object detection in autonomous driving. Results of this work are available in a github open repository.

Schlagwörter

Stichwörter der Autor:innen

3D object detectionKITTILiDARWaymoautonomous vehiclesdeep learningmonocular cameranuScenesradarsensor fusionstereo vision

Autor:innen und Institutionen

  • Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal.
  • Instituto de Engenharia Mecânica, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal.
  • Fraunhofer IKS, 80686 Munich, Germany.

ORCID-Profile: Miguel Valverde, Alexandra Moutinho, João-Vitor Zacchi

Förderung

  • Fundação para a Ciência e Tecnologia
  • Fundação para a Ciência e a Tecnologia (FCT) for its financial support via the project LAETA Base Funding

Zitieren

APA

Valverde, M., Moutinho, A., & Zacchi, J. V. (2025). A Survey of Deep Learning-Based 3D Object Detection Methods for Autonomous Driving Across Different Sensor Modalities. Sensors, 25(17), 5264. https://doi.org/10.3390/s25175264

Vancouver

Valverde M, Moutinho A, Zacchi JV. A Survey of Deep Learning-Based 3D Object Detection Methods for Autonomous Driving Across Different Sensor Modalities. Sensors. 2025;25(17):5264. doi:10.3390/s25175264

BibTeX
@article{Valverde2025,
  author = {Valverde, Miguel and Moutinho, Alexandra and Zacchi, João-Vitor},
  title = {A Survey of Deep Learning-Based 3D Object Detection Methods for Autonomous Driving Across Different Sensor Modalities},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {17},
  pages = {5264},
  doi = {10.3390/s25175264}
}
Kostenlos starten →