Task-Oriented Deep Joint Source-Channel Coding with Semantic-Aware Adaptive Quantization for Autonomous Driving
Sensors · 08.08.2026 · 26 (16) · 5035
DOI: 10.3390/s26165035 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 08.08.2026. Verfasst von Xin Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Science and Technology Base and Talent Special Project, National Natural Science Foundation of China, Natural Science Foundation of Guangxi.
Abstract (Originalsprache)
In autonomous driving and intelligent transportation, vehicles need to share visual perception information to extend sensing range, but conventional separate source-channel coding can suffer from the cliff effect under harsh vehicular channels, causing downstream perception failures. This paper proposes an end-to-end semantic communication system for autonomous-driving semantic segmentation. The system adopts SegFormer-B2 as the semantic encoder, performs feature modulation conditioned on the signal-to-noise ratio SNR, applies semantic-aware adaptive bit-width quantization based on Gumbel-Softmax, and uses a task-oriented decoder to directly produce segmentation maps. Experiments on Cityscapes evaluate the system under additive white Gaussian noise (AWGN) and per-channel independent block Rayleigh fading channels, with comparisons against a JPEG-based separate baseline and fixed-bit-width variants. Under AWGN, the proposed system maintains a mean intersection over union above 0.70 at SNR=−6dB, while the conventional baseline fails at SNR=0dB with an mIoU of 0.02, indicating improved robustness against the cliff effect. The results also show a non-monotonic relationship between quantization precision and segmentation performance: fixed 4-bit quantization can outperform fixed 6-bit quantization because finer quantization is more sensitive to channel noise. Under Rayleigh fading, adaptive quantization may suffer from semantic-channel mismatch, providing useful observations for future channel-aware semantic resource allocation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, China.
ORCID-Profile: Xin Wang, Haiqiang Chen, Youming Sun, Xiangcheng Li, Min Xie
Förderung
- Guangxi Science and Technology Base and Talent Special Project
- National Natural Science Foundation of China
- Natural Science Foundation of Guangxi
Zitieren
APA
Wang, X., Chen, H., Sun, Y., Li, X., & Xie, M. (2026). Task-Oriented Deep Joint Source-Channel Coding with Semantic-Aware Adaptive Quantization for Autonomous Driving. Sensors, 26(16), 5035. https://doi.org/10.3390/s26165035
Vancouver
Wang X, Chen H, Sun Y, Li X, Xie M. Task-Oriented Deep Joint Source-Channel Coding with Semantic-Aware Adaptive Quantization for Autonomous Driving. Sensors. 2026;26(16):5035. doi:10.3390/s26165035
BibTeX
@article{Wang2026,
author = {Wang, Xin and Chen, Haiqiang and Sun, Youming and Li, Xiangcheng and Xie, Min},
title = {Task-Oriented Deep Joint Source-Channel Coding with Semantic-Aware Adaptive Quantization for Autonomous Driving},
journal = {Sensors},
year = {2026},
volume = {26},
number = {16},
pages = {5035},
doi = {10.3390/s26165035}
}
EUVIMED