EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Object Detection Based on Lightweight YOLOX for Autonomous Driving

Qiyi He iD, Ao Xu iD, Zhiwei Ye, Wen Zhou, Ting Cai iD

Sensors · 01.09.2023 · 23 (17) · 7596

DOI: 10.3390/s23177596 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.09.2023. Verfasst von Qiyi He und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Hubei University of Technology, Wuhan 430068, China. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qiyi He, National Natural Science Foundation of China, Wuhan Science and Technology Bureau 2022 Knowledge Innovation Dawning Plan Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and rapid response in complex driving scenarios is a challenging problem in autonomous driving. If a target is detected, the vehicle will not be able to react in time, resulting in fatal safety accidents. Therefore, the application of driver assistance systems requires a model that can accurately detect targets in complex scenes and respond quickly. In this paper, a lightweight feature extraction model, ShuffDet, is proposed to replace the CSPDark53 model used by YOLOX by improving the YOLOX algorithm. At the same time, an attention mechanism is introduced into the path aggregation feature pyramid network (PAFPN) to make the network focus more on important information in the network, thereby improving the accuracy of the model. This model, which combines two methods, is called ShuffYOLOX, and it can improve the accuracy of the model while keeping it lightweight. The performance of the ShuffYOLOX model on the KITTI dataset is tested in this paper, and the experimental results show that compared to the original network, the mean average precision (mAP) of the ShuffYOLOX model on the KITTI dataset reaches 92.20%. In addition, the number of parameters of the ShuffYOLOX model is reduced by 34.57%, the Gflops are reduced by 42.19%, and the FPS is increased by 65%. Therefore, the ShuffYOLOX model is very suitable for autonomous driving applications.

Schlagwörter

Stichwörter der Autor:innen

YOLOXattention mechanismautonomous drivinglightweight network designobject detection

Autor:innen und Institutionen

  • School of Computer Science, Hubei University of Technology, Wuhan 430068, China.

ORCID-Profile: Qiyi He, Ao Xu, Ting Cai

Förderung

  • Qiyi He
  • National Natural Science Foundation of China
  • Wuhan Science and Technology Bureau 2022 Knowledge Innovation Dawning Plan Project

Zitieren

APA

He, Q., Xu, A., Ye, Z., Zhou, W., & Cai, T. (2023). Object Detection Based on Lightweight YOLOX for Autonomous Driving. Sensors, 23(17), 7596. https://doi.org/10.3390/s23177596

Vancouver

He Q, Xu A, Ye Z, Zhou W, Cai T. Object Detection Based on Lightweight YOLOX for Autonomous Driving. Sensors. 2023;23(17):7596. doi:10.3390/s23177596

BibTeX
@article{He2023,
  author = {He, Qiyi and Xu, Ao and Ye, Zhiwei and Zhou, Wen and Cai, Ting},
  title = {Object Detection Based on Lightweight YOLOX for Autonomous Driving},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {17},
  pages = {7596},
  doi = {10.3390/s23177596}
}
Kostenlos starten →