EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EMAF-Net: A Lightweight Single-Stage Detector for 13-Class Object Detection in Agricultural Rural Road Scenes

Zhixin Yao, Chunjiang Zhao iD, Yunjie Zhao iD, Xiaoyi Liu, Tuo Sun, Taihong Zhang

Sensors · 25.03.2026 · 26 (7) · 2055

DOI: 10.3390/s26072055 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.03.2026. Verfasst von Zhixin Yao und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, China. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Provincial Key S&T Program of Xinjiang, the National Key R&D Program of China, the Provincial Key S&T Program of Xinjiang.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rural road perception for agricultural machinery automation faces challenges including complex backgrounds, drastic lighting and weather variations, frequent occlusions, and high densities of small objects with significant scale variations. These factors make conventional detectors prone to missed detections and misclassifications. To address these issues, a 4K rural road dataset with 4771 images is constructed. The dataset covers 13 object categories and includes diverse day/night conditions and multiple weather scenarios on both structured and unstructured roads. EMAF-Net, a lightweight single-stage detector based on YOLOv4-P6, is proposed. The backbone integrates an EMHA module combining EfficientNet-B1 with multi-head self-attention (MHSA) for enhanced global context modeling while preserving efficient local feature extraction. The neck adopts an Improved ASPP and a bidirectional FPN to achieve robust multi-scale feature fusion and expanded receptive fields. Meanwhile, CIoU loss is used to optimize bounding box regression accuracy. The experimental results demonstrate that EMAF-Net achieves an mAP@0.5 of 64.05% and an mAP@0.5:0.95 of 48.95% on a rural road dataset. At the same time, it maintains a lightweight design with 18.3 M parameters and a computational complexity of 38.5 GFLOPs. Ablation studies confirm the EMHA module contributes a 6.22% mAP@0.5 improvement, validating EMAF-Net’s effectiveness for real-time rural road perception in autonomous agricultural systems.

Schlagwörter

Stichwörter der Autor:innen

EMAF-Netagricultural machinery automatic navigationmulti-head self-attention mechanismmulti-scale feature fusionobject detectionrural road

Autor:innen und Institutionen

  • College of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, China.
  • Xinjiang Agricultural Informatization Engineering, Technology Research Center, Urumqi 830052, China.
  • Research Center for Intelligent Agriculture, Ministry of Education Engineering, Urumqi 830052, China.
  • National Engineering Research Center for Information Technology in Agriculture, Beijing 100125, China.

ORCID-Profile: Chunjiang Zhao, Yunjie Zhao

Förderung

  • the Provincial Key S&T Program of Xinjiang
  • the National Key R&D Program of China
  • the Provincial Key S&T Program of Xinjiang
  • the National Key R&D Program of China

Zitieren

APA

Yao, Z., Zhao, C., Zhao, Y., Liu, X., Sun, T., & Zhang, T. (2026). EMAF-Net: A Lightweight Single-Stage Detector for 13-Class Object Detection in Agricultural Rural Road Scenes. Sensors, 26(7), 2055. https://doi.org/10.3390/s26072055

Vancouver

Yao Z, Zhao C, Zhao Y, Liu X, Sun T, Zhang T. EMAF-Net: A Lightweight Single-Stage Detector for 13-Class Object Detection in Agricultural Rural Road Scenes. Sensors. 2026;26(7):2055. doi:10.3390/s26072055

BibTeX
@article{Yao2026,
  author = {Yao, Zhixin and Zhao, Chunjiang and Zhao, Yunjie and Liu, Xiaoyi and Sun, Tuo and Zhang, Taihong},
  title = {EMAF-Net: A Lightweight Single-Stage Detector for 13-Class Object Detection in Agricultural Rural Road Scenes},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {2055},
  doi = {10.3390/s26072055}
}
Kostenlos starten →