EUVIMEDEUVIMED entdecken
Crossref

Wireless Vision-Centered Semantic Communication for Smart City Environment: Pretrained Network and Quantization

Yan Gong, Zheng Chu, Zhengyu Zhu, Pei Xiao, Ming Zeng, Yi Wang, Hari Pandey, Jingrui Hou

IEEE Transactions on Consumer Electronics · 2026-02 · 72 (1) · 2383-2398

DOI: 10.1109/tce.2026.3656549 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2026-02. Verfasst von Yan Gong und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Computational Resources provided by the School of Computing and Engineering, Bournemouth University, Zhejiang Provincial Natural Science Foundation of China, Natural Science Foundation of Ningbo Municipality.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper introduces a Vision-Centered Semantic Communication (VCSC) system tailored for efficient image transmission in smart city environments, where bandwidth is limited and channels are subject to severe noise. Unlike conventional text-centered or classical compression approaches, VCSC leverages a pretrained latent encoder–decoder network to extract compact, semantically rich representations directly from images. An innovative attention-based quantization strategy is employed to selectively allocate higher precision to critical regions, thereby reducing the overall bit rate while preserving essential semantic details. The quantized latent codes are robustly transmitted over wireless channels modeled with additive white Gaussian noise and Rayleigh fading. An end-to-end training framework minimizes both reconstruction and perceptual losses, ensuring high-fidelity image recovery even under adverse conditions. Extensive simulations demonstrate that VCSC outperforms traditional methods in preserving fine-grained details and semantic integrity, offering a promising solution for real-time surveillance, transportation, and infrastructure monitoring in smart cities.

Förderung

  • Computational Resources provided by the School of Computing and Engineering, Bournemouth University
  • Zhejiang Provincial Natural Science Foundation of China
  • Natural Science Foundation of Ningbo Municipality
  • National Natural Science Foundation of China
  • State key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications
  • Engineering and Physical Sciences Research Council
  • Natural Science Foundation of Henan Province
  • China Post-Doctoral Science Foundation

Zitieren

APA

Gong, Y., Chu, Z., Zhu, Z., Xiao, P., Zeng, M., Wang, Y., Pandey, H., & Hou, J. (2026). Wireless Vision-Centered Semantic Communication for Smart City Environment: Pretrained Network and Quantization. IEEE Transactions on Consumer Electronics, 72(1), 2383-2398. https://doi.org/10.1109/tce.2026.3656549

Vancouver

Gong Y, Chu Z, Zhu Z, Xiao P, Zeng M, Wang Y, et al. Wireless Vision-Centered Semantic Communication for Smart City Environment: Pretrained Network and Quantization. IEEE Transactions on Consumer Electronics. 2026;72(1):2383-2398. doi:10.1109/tce.2026.3656549

BibTeX
@article{Gong2026,
  author = {Gong, Yan and Chu, Zheng and Zhu, Zhengyu and Xiao, Pei and Zeng, Ming and Wang, Yi and Pandey, Hari and Hou, Jingrui},
  title = {Wireless Vision-Centered Semantic Communication for Smart City Environment: Pretrained Network and Quantization},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2026},
  volume = {72},
  number = {1},
  pages = {2383--2398},
  doi = {10.1109/tce.2026.3656549}
}
Kostenlos starten →