EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SMA-YOLO: A Novel Approach to Real-Time Vehicle Detection on Edge Devices

Haixia Liu, Yingkun Song, Yongxing Lin, Zhixin Tie iD

Sensors · 15.08.2025 · 25 (16) · 5072

DOI: 10.3390/s25165072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.08.2025. Verfasst von Haixia Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Keyi College, Zhejiang Sci-Tech University, Shaoxing 312369, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific research project of Zhejiang Provincial Department of Education, Scientific research project of Keyi College, Zhejiang Sci-Tech University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vehicle detection plays a pivotal role in traffic management as a key technology for intelligent traffic management and driverless driving. However, current deep learning-based vehicle detection models face several challenges in practical applications. These include slow detection speeds, large computational and parametric quantities, high leakage and misdetection rates in target-intensive environments, and difficulties in deploying them on edge devices with limited computing power and memory. To address these issues, this paper proposes an improved vehicle detection method called SMA-YOLO, based on the YOLOv7 model. Firstly, MobileNetV3 is adopted as the new backbone network to lighten the model. Secondly, the SimAM attention mechanism is incorporated to suppress background interference and enhance small-target detection capability. Additionally, the ACON activation function is substituted for the original SiLU activation function in the YOLOv7 model to improve detection accuracy. Lastly, SIoU is used to replace CIoU to optimize the loss of function and accelerate model convergence. Experiments on the UA-DETRAC dataset demonstrate that the proposed SMA-YOLO model achieves a lightweight effect, significantly reducing model size, computational requirements, and the number of parameters. It not only greatly improves detection speed but also maintains higher detection accuracy. This provides a feasible solution for deploying a vehicle detection model on embedded devices for real-time detection.

Schlagwörter

Stichwörter der Autor:innen

ACON activation functionMobileNetV3SimAM attention mechanismYOLOv7light weightingvehicle detection

Autor:innen und Institutionen

  • Keyi College, Zhejiang Sci-Tech University, Shaoxing 312369, China.
  • School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China.

ORCID-Profile: Zhixin Tie

Förderung

  • Scientific research project of Zhejiang Provincial Department of Education
  • Scientific research project of Keyi College, Zhejiang Sci-Tech University

Zitieren

APA

Liu, H., Song, Y., Lin, Y., & Tie, Z. (2025). SMA-YOLO: A Novel Approach to Real-Time Vehicle Detection on Edge Devices. Sensors, 25(16), 5072. https://doi.org/10.3390/s25165072

Vancouver

Liu H, Song Y, Lin Y, Tie Z. SMA-YOLO: A Novel Approach to Real-Time Vehicle Detection on Edge Devices. Sensors. 2025;25(16):5072. doi:10.3390/s25165072

BibTeX
@article{Liu2025,
  author = {Liu, Haixia and Song, Yingkun and Lin, Yongxing and Tie, Zhixin},
  title = {SMA-YOLO: A Novel Approach to Real-Time Vehicle Detection on Edge Devices},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {5072},
  doi = {10.3390/s25165072}
}
Kostenlos starten →