EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RDCRNet: RGB-T Object Detection Network Based on Cross-Modal Representation Model

Yubin Li iD, Weida Zhan iD, Yichun Jiang iD, Jinxin Guo iD

Entropy · 19.04.2025 · 27 (4) · 442

DOI: 10.3390/e27040442 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 19.04.2025. Verfasst von Yubin Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: The College of Electronic and Information Engineering, Changchun University of Science and Technology, Changchun 130022, China. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Provincial Science and Technology Department Development Program, Jilin Provincial Development and Reform Commission Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RGB-thermal object detection harnesses complementary information from visible and thermal modalities to enhance detection robustness in challenging environments, particularly under low-light conditions. However, existing approaches suffer from limitations due to their heavy dependence on precisely registered data and insufficient handling of cross-modal distribution disparities. This paper presents RDCRNet, a novel framework incorporating a Cross-Modal Representation Model to effectively address these challenges. The proposed network features a Cross-Modal Feature Remapping Module that aligns modality distributions through statistical normalization and learnable correction parameters, significantly reducing feature discrepancies between modalities. A Cross-Modal Refinement and Interaction Module enables sophisticated bidirectional information exchange via trinity refinement for intra-modal context modeling and cross-attention mechanisms for unaligned feature fusion. Multiscale detection capability is enhanced through a Cross-Scale Feature Integration Module, improving detection performance across various object sizes. To overcome the inherent data scarcity in RGB-T detection, we introduce a self-supervised pretraining strategy that combines masked reconstruction with adversarial learning and semantic consistency loss, effectively leveraging both aligned and unaligned RGB-T samples. Extensive experiments demonstrate that RDCRNet achieves state-of-the-art performance on multiple benchmark datasets while maintaining high computational and storage efficiency, validating its superiority and practical effectiveness in real-world applications.

Schlagwörter

Stichwörter der Autor:innen

cross-modal representationmultimodalobject detectionpretraining

Autor:innen und Institutionen

  • The College of Electronic and Information Engineering, Changchun University of Science and Technology, Changchun 130022, China.

ORCID-Profile: Yubin Li, Weida Zhan, Yichun Jiang, Jinxin Guo

Förderung

  • Jilin Provincial Science and Technology Department Development Program
  • Jilin Provincial Development and Reform Commission Program

Zitieren

APA

Li, Y., Zhan, W., Jiang, Y., & Guo, J. (2025). RDCRNet: RGB-T Object Detection Network Based on Cross-Modal Representation Model. Entropy, 27(4), 442. https://doi.org/10.3390/e27040442

Vancouver

Li Y, Zhan W, Jiang Y, Guo J. RDCRNet: RGB-T Object Detection Network Based on Cross-Modal Representation Model. Entropy. 2025;27(4):442. doi:10.3390/e27040442

BibTeX
@article{Li2025,
  author = {Li, Yubin and Zhan, Weida and Jiang, Yichun and Guo, Jinxin},
  title = {RDCRNet: RGB-T Object Detection Network Based on Cross-Modal Representation Model},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {4},
  pages = {442},
  doi = {10.3390/e27040442}
}
Kostenlos starten →