EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A lightweight RGB-D cross-modal learning network for rail defect detection

Yingcheng Zhao, Xinhong Hei

Transportation Safety and Environment · 05.11.2026

DOI: 10.1093/tse/tdag065 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transportation Safety and Environment, online erschienen am 05.11.2026. Verfasst von Yingcheng Zhao und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rail surface defects pose serious risks to railway transportation safety, and accurate real-time detection is essential for reliable railway maintenance. Existing RGB-only or depth-only methods are often limited by low contrast, uneven illumination, subtle defect patterns, insufficient annotated data, suboptimal cross-modal fusion, and high computational cost. To address these challenges, this study proposes BiMaL, a Bidirectional Modality-aware Lightweight framework for RGB-D rail surface defect detection. BiMaL consists of three stages: bidirectional cross-modal self-supervised pre-training, lightweight RGB-D fusion network construction, and importance-aware dependency-preserving structured pruning. First, a BYOL-based self-supervised strategy learns discriminative RGB and depth representations from unlabeled data, reducing reliance on manual annotations. Second, a compact fusion network integrates RGB texture cues and depth structural information through lightweight local complementary and global correlation pathways. Third, a channel-importance-aware pruning strategy compresses redundant encoder channels through dependency graph constraints while deliberately preserving key fusion and detection components for edge deployment. Experiments on the NEU RSDDS-AUG dataset show that BiMaL achieves a Structure Measure of 0.865, maximum F-measure of 0.901, maximum enhanced-alignment measure of 0.943, and mean absolute error of 0.061. The final model contains only 2.2 million parameters and reaches 101.8 frames per second. These results demonstrate that BiMaL achieves a favorable balance between detection accuracy and computational efficiency, providing a practical solution for real-time rail surface defect inspection on resource-constrained mobile platforms.

Zitieren

APA

Zhao, Y., & Hei, X. (2026). A lightweight RGB-D cross-modal learning network for rail defect detection. Transportation Safety and Environment. https://doi.org/10.1093/tse/tdag065

Vancouver

Zhao Y, Hei X. A lightweight RGB-D cross-modal learning network for rail defect detection. Transportation Safety and Environment. 2026. doi:10.1093/tse/tdag065

BibTeX
@article{Zhao2026,
  author = {Zhao, Yingcheng and Hei, Xinhong},
  title = {A lightweight RGB-D cross-modal learning network for rail defect detection},
  journal = {Transportation Safety and Environment},
  year = {2026},
  doi = {10.1093/tse/tdag065}
}
Kostenlos starten →