EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bidirectional Spatial Context Modeling and Contrast-Driven Feature Aggregation for Prohibited Item Detection in Cluttered X-Ray Baggage Images

Hui Zhang, Xinmeng Wang

Algorithms · 18.11.2026 · 19 (11) · 1016

DOI: 10.3390/a19111016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 18.11.2026. Verfasst von Hui Zhang und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated threat detection in X-ray security inspection is difficult. Objects often overlap in packed baggage. Many threats have very low contrast against surrounding items. As a result, detectors designed for natural images often miss small and occluded threats. This paper proposes the Scanline-Context X-ray Network (SCXNet), a detector designed for X-ray inspection. SCXNet uses a hierarchical encoder to preserve channel-specific features in shallow features and to build stronger representations in deeper features. It also uses Contrast-Driven Feature Aggregation to enhance weak boundaries through gradient-guided fusion. In addition, a Bidirectional Spatial Context Module aggregates context along the image-width axis with convolutional long short-term memory (ConvLSTM) to separate overlapping objects in clutter. SCXNet is trained with Varifocal Loss for classification and complete intersection over union (CIoU) loss for box regression. We evaluate SCXNet on two public datasets, Prohibited Item Detection Ray (PIDray) and Occluded Prohibited Items X-ray (OPIXray). SCXNet achieves higher mean average precision (mAP) than state-of-the-art detectors on both datasets. On PIDray, SCXNet reaches 73.48% mAP50 and improves over AO-DETR by 3.19% in relative terms. On OPIXray, it reaches 91.56% mAP50. These results show that domain tailored architecture design is effective for X-ray threat detection.

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Zhang, H., & Wang, X. (2026). Bidirectional Spatial Context Modeling and Contrast-Driven Feature Aggregation for Prohibited Item Detection in Cluttered X-Ray Baggage Images. Algorithms, 19(11), 1016. https://doi.org/10.3390/a19111016

Vancouver

Zhang H, Wang X. Bidirectional Spatial Context Modeling and Contrast-Driven Feature Aggregation for Prohibited Item Detection in Cluttered X-Ray Baggage Images. Algorithms. 2026;19(11):1016. doi:10.3390/a19111016

BibTeX
@article{Zhang2026,
  author = {Zhang, Hui and Wang, Xinmeng},
  title = {Bidirectional Spatial Context Modeling and Contrast-Driven Feature Aggregation for Prohibited Item Detection in Cluttered X-Ray Baggage Images},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {11},
  pages = {1016},
  doi = {10.3390/a19111016}
}
Kostenlos starten →