EUVIMEDEUVIMED entdecken
Crossref

BEVStereo: Enhancing Depth Estimation in Multi-View 3D Object Detection with Temporal Stereo

Yinhao Li, Han Bao, Zheng Ge, Jinrong Yang, Jianjian Sun, Zeming Li

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (2) · 1486-1494

DOI: 10.1609/aaai.v37i2.25234 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Yinhao Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 242-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Restricted by the ability of depth perception, all Multi-view 3D object detection methods fall into the bottleneck of depth accuracy. By constructing temporal stereo, depth estimation is quite reliable in indoor scenarios. However, there are two difficulties in directly integrating temporal stereo into outdoor multi-view 3D object detectors: 1) The construction of temporal stereos for all views results in high computing costs. 2) Unable to adapt to challenging outdoor scenarios. In this study, we propose an effective method for creating temporal stereo by dynamically determining the center and range of the temporal stereo. The most confident center is found using the EM algorithm. Numerous experiments on nuScenes have shown the BEVStereo's ability to deal with complex outdoor scenarios that other stereo-based methods are unable to handle. For the first time, a stereo-based approach shows superiority in scenarios like a static ego vehicle and moving objects. BEVStereo achieves the new state-of-the-art in the camera-only track of nuScenes dataset while maintaining memory efficiency. Codes have been released.

Zitieren

APA

Li, Y., Bao, H., Ge, Z., Yang, J., Sun, J., & Li, Z. (2023). BEVStereo: Enhancing Depth Estimation in Multi-View 3D Object Detection with Temporal Stereo. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 1486-1494. https://doi.org/10.1609/aaai.v37i2.25234

Vancouver

Li Y, Bao H, Ge Z, Yang J, Sun J, Li Z. BEVStereo: Enhancing Depth Estimation in Multi-View 3D Object Detection with Temporal Stereo. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(2):1486-1494. doi:10.1609/aaai.v37i2.25234

BibTeX
@article{Li2023,
  author = {Li, Yinhao and Bao, Han and Ge, Zheng and Yang, Jinrong and Sun, Jianjian and Li, Zeming},
  title = {BEVStereo: Enhancing Depth Estimation in Multi-View 3D Object Detection with Temporal Stereo},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {2},
  pages = {1486--1494},
  doi = {10.1609/aaai.v37i2.25234}
}
Kostenlos starten →