Semantic Scene Completion in Autonomous Driving: A Two-Stream Multi-Vehicle Collaboration Approach
Sensors · 02.12.2024 · 24 (23) · 7702
DOI: 10.3390/s24237702 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 02.12.2024. Verfasst von Junxuan Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Provincial Engineering Research Center for Optoelectronic Instrument, School of Electronic Science and Engineering (School of Microelectron…. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Startup Foundation for Introducing Talent of NUIST, Startup Foundation for Introducing Talent of NUIST, Shandong Province Science Foundation for Youths.
Abstract (Originalsprache)
Vehicle-to-vehicle communication enables capturing sensor information from diverse perspectives, greatly aiding in semantic scene completion in autonomous driving. However, the misalignment of features between ego vehicle and cooperative vehicles leads to ambiguity problems, affecting accuracy and semantic information. In this paper, we propose a Two-Stream Multi-Vehicle collaboration approach (TSMV), which divides the features of collaborative vehicles into two streams and regresses interactively. To overcome the problems caused by feature misalignment, the Neighborhood Self-Cross Attention Transformer (NSCAT) module is designed to enable the ego vehicle to query the most similar local features from collaborative vehicles through cross-attention, rather than assuming spatial-temporal synchronization. A 3D occupancy map is finally generated from the features of collaborative vehicle aggregation. Experimental results on both V2VSSC and SemanticOPV2V datasets demonstrate TSMV outpace state-of-the-art collaborative semantic scene completion techniques.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Guangdong Provincial Engineering Research Center for Optoelectronic Instrument, School of Electronic Science and Engineering (School of Microelectronics), South China Normal University, Foshan 528225, China.
- School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China.
- Inspur Group, Ji'nan 250000, China.
ORCID-Profile: Junxuan Li, Kaiqing Luo
Förderung
- The Startup Foundation for Introducing Talent of NUIST
- Startup Foundation for Introducing Talent of NUIST
- Shandong Province Science Foundation for Youths
Zitieren
APA
Li, J., Zhang, Y., Han, J., Han, P., & Luo, K. (2024). Semantic Scene Completion in Autonomous Driving: A Two-Stream Multi-Vehicle Collaboration Approach. Sensors, 24(23), 7702. https://doi.org/10.3390/s24237702
Vancouver
Li J, Zhang Y, Han J, Han P, Luo K. Semantic Scene Completion in Autonomous Driving: A Two-Stream Multi-Vehicle Collaboration Approach. Sensors. 2024;24(23):7702. doi:10.3390/s24237702
BibTeX
@article{Li2024,
author = {Li, Junxuan and Zhang, Yuanfang and Han, Jiayi and Han, Peng and Luo, Kaiqing},
title = {Semantic Scene Completion in Autonomous Driving: A Two-Stream Multi-Vehicle Collaboration Approach},
journal = {Sensors},
year = {2024},
volume = {24},
number = {23},
pages = {7702},
doi = {10.3390/s24237702}
}
EUVIMED