Adaptive Wireless Image Semantic Transmission and Over-The-Air Testing

TL;DR

This paper introduces ASCViT-JSCC, an adaptive semantic image transmission scheme using vision transformers and OTA testing, which prioritizes important image regions for improved robustness and quality.

Contribution

The paper presents a novel adaptive transmission scheme combining vision transformers with OFDM, object importance detection, and OTA testing, advancing semantic image communication.

Findings

Significantly improves object preservation in transmitted images.

Enhances image reconstruction quality over existing methods.

Validated through both simulations and real OTA tests.

Abstract

Semantic communication has undergone considerable evolution due to the recent rapid development of artificial intelligence (AI), significantly enhancing both communication robustness and efficiency. Despite these advancements, most current semantic communication methods for image transmission pay little attention to the differing importance of objects and backgrounds in images. To address this issue, we propose a novel scheme named ASCViT-JSCC, which utilizes vision transformers (ViTs) integrated with an orthogonal frequency division multiplexing (OFDM) system. This scheme adaptively allocates bandwidth for objects and backgrounds in images according to the importance order of different parts determined by object detection of you only look once version 5 (YOLOv5) and feature points detection of scale invariant feature transform (SIFT). Furthermore, the proposed scheme adheres to digital modulation standards by incorporating quantization modules. We validate this approach through an over-the-air (OTA) testbed named intelligent communication prototype validation platform (ICP) based on a software-defined radio (SDR) and NVIDIA embedded kits. Our findings from both simulations and practical measurements show that ASCViT-JSCC significantly preserves objects in images and enhances reconstruction quality compared to existing methods.