EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Road Scene Understanding of Autonomous Vehicles Based on Multi-Task Learning

Jinghua Guo iD, Jingyao Wang iD, Huinian Wang, Baoping Xiao, Zhifei He, Lubin Li

Sensors · 07.07.2023 · 23 (13) · 6238

DOI: 10.3390/s23136238 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.07.2023. Verfasst von Jinghua Guo und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical and Electrical Engineering, Xiamen University, Xiamen 361005, China. Hauptthemen laut MEDLINE: Autonomous Vehicles, Learning. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Major Science and Technology Projects of Xiamen of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Road scene understanding is crucial to the safe driving of autonomous vehicles. Comprehensive road scene understanding requires a visual perception system to deal with a large number of tasks at the same time, which needs a perception model with a small size, fast speed, and high accuracy. As multi-task learning has evident advantages in performance and computational resources, in this paper, a multi-task model YOLO-Object, Drivable Area, and Lane Line Detection (YOLO-ODL) based on hard parameter sharing is proposed to realize joint and efficient detection of traffic objects, drivable areas, and lane lines. In order to balance tasks of YOLO-ODL, a weight balancing strategy is introduced so that the weight parameters of the model can be automatically adjusted during training, and a Mosaic migration optimization scheme is adopted to improve the evaluation indicators of the model. Our YOLO-ODL model performs well on the challenging BDD100K dataset, achieving the state of the art in terms of accuracy and computational efficiency.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Autonomous VehiclesLearningRecordsSoftware

Stichwörter der Autor:innen

autonomous vehiclesdrivable area detectionlane line detectionmulti-task learningtraffic object detectionvisual perception

Autor:innen und Institutionen

  • Department of Mechanical and Electrical Engineering, Xiamen University, Xiamen 361005, China.
  • Department of Automation, Xiamen University, Xiamen 361005, China.

ORCID-Profile: Jinghua Guo, Jingyao Wang

Förderung

  • Major Science and Technology Projects of Xiamen of China

Zitieren

APA

Guo, J., Wang, J., Wang, H., Xiao, B., He, Z., & Li, L. (2023). Research on Road Scene Understanding of Autonomous Vehicles Based on Multi-Task Learning. Sensors, 23(13), 6238. https://doi.org/10.3390/s23136238

Vancouver

Guo J, Wang J, Wang H, Xiao B, He Z, Li L. Research on Road Scene Understanding of Autonomous Vehicles Based on Multi-Task Learning. Sensors. 2023;23(13):6238. doi:10.3390/s23136238

BibTeX
@article{Guo2023,
  author = {Guo, Jinghua and Wang, Jingyao and Wang, Huinian and Xiao, Baoping and He, Zhifei and Li, Lubin},
  title = {Research on Road Scene Understanding of Autonomous Vehicles Based on Multi-Task Learning},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {13},
  pages = {6238},
  doi = {10.3390/s23136238}
}
Kostenlos starten →