Semantic segmentation-based semantic communication system for image transmission

TLDR

Semantic communication, an emerging paradigm driven by AI and IoT, has attracted interest, yet current image transmission systems encode entire images without distinguishing important pixels or regions of interest. The study proposes a semantic communication system that uses semantic segmentation to separate regions of interest from non‑interest in image transmission. The system classifies pixels with a segmentation algorithm, routes ROI and non‑interest through separate networks with different bandwidths, and introduces a θPSNR metric to evaluate transmission accuracy. Experiments demonstrate that the proposed system outperforms existing semantic and conventional image transmission methods.

Abstract

With the rapid development of artificial intelligence and the widespread use of the Internet of Things, semantic communication, as an emerging communication paradigm, has been attracting great interest. Taking image transmission as an example, from the semantic communication's view, not all pixels in the images are equally important for certain receivers. The existing semantic communication systems directly perform semantic encoding and decoding on the whole image, in which the region of interest cannot be identified. In this paper, we propose a novel semantic communication system for image transmission that can distinguish between regions of interest (ROI) and regions of non-interest (RONI) based on semantic segmentation, where a semantic segmentation algorithm is used to classify each pixel of the image and distinguish ROI and RONI. The system also enables high-quality transmission of ROI with lower communication overheads by transmissions through different semantic communication networks with different bandwidth requirements. An improved metric θPSNR is proposed to evaluate the transmission accuracy of the novel semantic transmission network. Experimental results show that our proposed system achieves a significant performance improvement compared with existing approaches, namely, existing semantic communication approaches and the conventional approach without semantics.