EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

FDD-YOLO: A Lightweight Multi-scale Prohibited Items Detection Model

Zilong Xue, Bo Wang, Yuanwei Xie, Zhibin Li, Xiaozheng Fan, Chenyoukang Lin, Peiyang Wei, Linlin Chen, Xun Deng, Jianhong Gan

EAI Endorsed Transactions on AI and Robotics · 11.11.2025 · 4

DOI: 10.4108/airo.10277 ↗

Kurz gefasst

Fachartikel in der Zeitschrift EAI Endorsed Transactions on AI and Robotics, online erschienen am 11.11.2025. Verfasst von Zilong Xue und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

X-ray security inspection faces challenges such as severe occlusion, scale variation, and complex background when detecting prohibited items, requiring real-time and accurate detection. Although the YOLO series of models has high inference efficiency, they suffer from problems such as feature redundancy, insufficient fine-grained feature extraction, and limited adaptability to overlapping objects. To overcome these limitations, we propose FDD-YOLO and design three novel modules: (1) The Frequency Domain Decomposition Network (FDDN) in the backbone network enhances the edges of metal objects and the contours of liquid containers by decomposing high-frequency and low-frequency features while reducing computational redundancy; (2) The Deformable Elastic Fusion Pyramid (DEFP) in the neck network adopts dynamic channel allocation and multi-scale deformable convolution to handle the geometric changes of folded and overlapping objects; (3) The lightweight Dual-channel Convolution (DualConv) improves multi-scale feature capture through grouping and point-by-point convolution, thereby reducing the number of parameters while improving the accuracy of small object detection. Tests on the SIXray, HIXray, and private GIX datasets show that FDD-YOLO achieves 2.6%, 3.2%, and 8.6% higher mAP than YOLOv11n, respectively, achieving accuracies of 94.8%, 84%, and 71.8%, respectively. This framework also reduces the number of parameters by 30.6% and the number of FLOPs by 26.9%, achieving an optimal balance between accuracy and efficiency, setting a new technical benchmark for real-time security inspections.

Zitieren

APA

Xue, Z., Wang, B., Xie, Y., Li, Z., Fan, X., Lin, C., Wei, P., Chen, L., Deng, X., & Gan, J. (2025). FDD-YOLO: A Lightweight Multi-scale Prohibited Items Detection Model. EAI Endorsed Transactions on AI and Robotics, 4. https://doi.org/10.4108/airo.10277

Vancouver

Xue Z, Wang B, Xie Y, Li Z, Fan X, Lin C, et al. FDD-YOLO: A Lightweight Multi-scale Prohibited Items Detection Model. EAI Endorsed Transactions on AI and Robotics. 2025;4. doi:10.4108/airo.10277

BibTeX
@article{Xue2025,
  author = {Xue, Zilong and Wang, Bo and Xie, Yuanwei and Li, Zhibin and Fan, Xiaozheng and Lin, Chenyoukang and Wei, Peiyang and Chen, Linlin and Deng, Xun and Gan, Jianhong},
  title = {FDD-YOLO: A Lightweight Multi-scale Prohibited Items Detection Model},
  journal = {EAI Endorsed Transactions on AI and Robotics},
  year = {2025},
  volume = {4},
  doi = {10.4108/airo.10277}
}
Kostenlos starten →