EUVIMEDEUVIMED entdecken
Open Access

MonoAux: Fully Exploiting Auxiliary Information and Uncertainty for Monocular 3D Object Detection

Zhenglin Li iD, Wenbo Zheng iD, Le Yang iD, Liyan Ma iD, Yang Zhou iD, Yan Peng iD

Cyborg and Bionic Systems · 2024-01 · 5

DOI: 10.34133/cbsystems.0097 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cyborg and Bionic Systems, online erschienen am 27.03.2024. Verfasst von Zhenglin Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Artificial Intelligence, Shanghai University, Shanghai, China. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Shanghai Sailing Program, Natural Science Foundation of Shanghai Municipality.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monocular 3D object detection plays a pivotal role in autonomous driving, presenting a formidable challenge by requiring the precise localization of 3D objects within a single image, devoid of depth information. Most existing methods in this domain fall short of harnessing the limited information available in monocular 3D detection tasks. They typically provide only a single detection outcome, omitting essential uncertainty analysis and result post-processing during model inference, thus limiting overall model performance. In this paper, we propose a comprehensive framework that maximizes information extraction from monocular images while encompassing diverse depth estimation and incorporating uncertainty analysis. Specifically, we mine additional information intrinsic to the monocular 3D detection task to augment supervision, thereby addressing the information scarcity challenge. Moreover, our framework handles depth estimation by recovering multiple sets of depth values from calculated visual heights. The final depth estimate and 3D confidence are determined through an uncertainty fusion process, effectively reducing inference errors. Furthermore, to address task weight allocation in multi-task training, we present a versatile training strategy tailored to monocular 3D detection. This approach leverages measurement indicators to monitor task progress, adaptively adjusting loss weights for different tasks. Experimental results on the KITTI and Waymo dataset confirm the effectiveness of our approach. The proposed method consistently provides enhanced performance across various difficulty levels compared to the original framework while maintaining real-time efficiency.

Autor:innen und Institutionen

  • Institute of Artificial Intelligence, Shanghai University, Shanghai, China.
  • School of Future Technology, Shanghai University, Shanghai, China.
  • Department of Electrical and Computer Engineering, University of Canterbury, Christchurch, New Zealand.

ORCID-Profile: Zhenglin Li, Wenbo Zheng, Le Yang, Liyan Ma, Yang Zhou, Yan Peng

Förderung

  • National Natural Science Foundation of China
  • Shanghai Sailing Program
  • Natural Science Foundation of Shanghai Municipality

Zitieren

APA

Li, Z., Zheng, W., Yang, L., Ma, L., Zhou, Y., & Peng, Y. (2024). MonoAux: Fully Exploiting Auxiliary Information and Uncertainty for Monocular 3D Object Detection. Cyborg and Bionic Systems, 5. https://doi.org/10.34133/cbsystems.0097

Vancouver

Li Z, Zheng W, Yang L, Ma L, Zhou Y, Peng Y. MonoAux: Fully Exploiting Auxiliary Information and Uncertainty for Monocular 3D Object Detection. Cyborg and Bionic Systems. 2024;5. doi:10.34133/cbsystems.0097

BibTeX
@article{Li2024,
  author = {Li, Zhenglin and Zheng, Wenbo and Yang, Le and Ma, Liyan and Zhou, Yang and Peng, Yan},
  title = {MonoAux: Fully Exploiting Auxiliary Information and Uncertainty for Monocular 3D Object Detection},
  journal = {Cyborg and Bionic Systems},
  year = {2024},
  volume = {5},
  doi = {10.34133/cbsystems.0097}
}
Kostenlos starten →