Adaptive image sharing improves safety over variable vehicle networks
Adaptive Semantic Communication with Residual Quantization for Resilient Vehicular Networks
Networking and Internet Architecture
Summary
Vehicles need to share camera images quickly to stay safe, but sending high-quality pictures uses a lot of network data, which can be slow or unreliable. This paper presents a new way to send images that changes how much detail is sent depending on how good the network is at the moment. The method compresses images into several quality levels and picks the best one to fit network limits, making communication faster and more reliable. The authors show their approach helps vehicles share useful visual information while adapting to changing connection quality.
What this means in practice
- •For automotive communication engineers: Build vehicle communication systems that adjust image quality based on real-time network conditions to improve timely safety data sharing.
- •For mobile network operators: Optimize bandwidth allocation for vehicle-to-everything (V2X) multicast by supporting adaptive image transmission methods responding to changing link quality.
Authors
Xuanhao Luo, Ruichen Gao, Sandeep Sreenivasan, Zhizhen Li, Yuchen Liu
Abstract
Vehicular networks require timely visual information exchange to support safety-critical applications such as cooperative perception and hazard awareness, yet transmitting high-dimensional camera data over bandwidth-limited and dynamic wireless links remains challenging. In this paper, we propose an adaptive semantic communication architecture for vehicular multicast that adjusts the amount of visual information transmitted according to current channel conditions, available communication resources, and latency requirements. Specifically, the visual encoder uses residual quantization to represent each image at multiple bitrate and reconstruction-quality levels. At runtime, the system selects an appropriate level based on the communication conditions, enabling it to trade visual fidelity for lower transmission overhead when network resources are limited. Context-adaptive entropy coding further compresses the quantized representations using offline-learned statistics, without requiring retraining for different channel conditions. This design allows the visual representation to be learned offline while the communication strategy is adapted online. Experimental results demonstrate competitive rate-distortion performance at ultra-low bitrates, improved delivery reliability and deadline satisfaction across diverse vehicular scenarios, and strong downstream perception performance, achieving up to 0.88 mAP50 while dynamically adapting to changing communication conditions.