EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integration of ShuffleNet V2 and YOLOv5s Networks for a Lightweight Object Detection Model of Electric Bikes within Elevators

Jingfang Su, Minrui Yang, Xinliang Tang

Electronics · 18.01.2024 · 13 (2) · 394

DOI: 10.3390/electronics13020394 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 18.01.2024. Verfasst von Jingfang Su und 2 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Youth Fund Project of the Hebei Provincial Department of Education, Science and Technology Research Project of Hebei Province Colleges and Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The entry of electric bikes into elevators poses safety risks. This article proposes a lightweight object detection model for edge deployment in elevator environments specifically designed for electric bikes. Based on the YOLOv5s network, the backbone network replaces the original CSPDarknet53 with a lightweight multilayer ShuffleNet V2 convolutional neural network, achieving a lightweight backbone network. Swin Transformer modules are introduced between layers to enhance the feature expression capability of images, and a SimAM attention mechanism is applied at the end layer to further improve the feature extraction capability of the backbone network. In the neck network, lightweight and depth-balanced GSConv and VoV-GSCSP modules replace several Conv and C3 basic convolutional modules, reducing the parameter count while enhancing the cross-scale connection and fusion capabilities of feature maps. The prediction network uses the faster-converging and more accurate EIOU error function as the position loss function for iterative training. This article conducts various lightweighting comparison experiments and ablation experiments on the improved object detection model. The experimental results demonstrate that the proposed object detection model, with a model size of only 2.6 megabytes and 1.1 million parameters, achieves a frame rate of 106 frames per second and a detection accuracy of 95.5%. This represents an 84.8% reduction in computational load compared to the original YOLOv5s model. The model’s volume and parameter count are reduced by 81.0% and 84.3%, respectively, with only a 0.9% decrease in mAP. The improved object detection model proposed in this paper can meet the real-time detection requirements for electric bikes in elevator scenarios, providing a feasible technical solution for its deployment on edge devices within elevators.

Förderung

  • Youth Fund Project of the Hebei Provincial Department of Education
  • Science and Technology Research Project of Hebei Province Colleges and Universities

Zitieren

APA

Su, J., Yang, M., & Tang, X. (2024). Integration of ShuffleNet V2 and YOLOv5s Networks for a Lightweight Object Detection Model of Electric Bikes within Elevators. Electronics, 13(2), 394. https://doi.org/10.3390/electronics13020394

Vancouver

Su J, Yang M, Tang X. Integration of ShuffleNet V2 and YOLOv5s Networks for a Lightweight Object Detection Model of Electric Bikes within Elevators. Electronics. 2024;13(2):394. doi:10.3390/electronics13020394

BibTeX
@article{Su2024,
  author = {Su, Jingfang and Yang, Minrui and Tang, Xinliang},
  title = {Integration of ShuffleNet V2 and YOLOv5s Networks for a Lightweight Object Detection Model of Electric Bikes within Elevators},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {2},
  pages = {394},
  doi = {10.3390/electronics13020394}
}
Kostenlos starten →