EUVIMEDEUVIMED entdecken
Crossref

Real-Time Multispectral Semantic Segmentation Network Utilizing Feature Frequency Decomposition and Spatial Division Distillation for Autonomous Driving

Yiqian Yang, Weichao Sun

IEEE Transactions on Intelligent Transportation Systems · 2025-11 · 26 (11) · 20363-20374

DOI: 10.1109/tits.2025.3599549 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2025-11. Verfasst von Yiqian Yang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: Chinese Aeronautical Establishment, State Key Laboratory of General Artificial Intelligence.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In autonomous driving systems, multispectral semantic segmentation integrates thermal images with RGB images to mitigate reliability degradation under challenging illumination conditions. However, most RGB-T methods cannot maintain high accuracy without sacrificing efficiency, thereby hindering efficient scene understanding. This paper presents RADNet, an asymmetric dual-stream network optimized for real-time RGB-T semantic segmentation, which incorporates three important components. The FFD module analyzes thermal features from the perspective of frequency to enhance thermal representations while suppressing interference. Furthermore, the ISD strategy explicitly transfers multimodal knowledge under varying illumination, leveraging the strengths of each modality without adding inference overhead. In addition, the FR module combines standard convolutions and central difference convolutions via structural re-parameterization to enhance detailed information. RADNet shows noticeable efficiency with 198.49 FPS on an RTX 3090 GPU while maintaining 13.21M parameters. Experimental results across three multispectral benchmarks covering diverse scenarios and illumination variations validate its competitive accuracy. Our network strikes a promising balance between segmentation performance and computational efficiency, making it a promising solution for further exploration in autonomous driving systems.

Förderung

  • Chinese Aeronautical Establishment
  • State Key Laboratory of General Artificial Intelligence

Zitieren

APA

Yang, Y., & Sun, W. (2025). Real-Time Multispectral Semantic Segmentation Network Utilizing Feature Frequency Decomposition and Spatial Division Distillation for Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems, 26(11), 20363-20374. https://doi.org/10.1109/tits.2025.3599549

Vancouver

Yang Y, Sun W. Real-Time Multispectral Semantic Segmentation Network Utilizing Feature Frequency Decomposition and Spatial Division Distillation for Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems. 2025;26(11):20363-20374. doi:10.1109/tits.2025.3599549

BibTeX
@article{Yang2025,
  author = {Yang, Yiqian and Sun, Weichao},
  title = {Real-Time Multispectral Semantic Segmentation Network Utilizing Feature Frequency Decomposition and Spatial Division Distillation for Autonomous Driving},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2025},
  volume = {26},
  number = {11},
  pages = {20363--20374},
  doi = {10.1109/tits.2025.3599549}
}
Kostenlos starten →