Semantic-Preserving Image Compression and Restoration Pipeline for Bandwidth-Constrained UAV Applications: A Task-Aware Evaluation Framework

Abstract

Unmanned aerial vehicles (UAVs) face critical challenges in transmitting high-resolution imagery over bandwidth-constrained communication channels, particularly in time-sensitive applications such as search and rescue and surveillance. This paper presents a data-efficient image transmission and enhancement pipeline addressing the trade-off between transmission efficiency and visual quality preservation. Our three-stage framework consists of onboard k-means color quantization (16-color palette), efficient transmission over bandwidth-limited channels, and ground-station deep learning-based restoration using CCDNet with iterative residual learning. The pipeline achieves approximately 68% file size reduction and 3× faster transmission times under realistic network conditions, validated through probabilistic network simulations. Beyond perceptual quality metrics (PSNR: 35.01 dB, SSIM: 0.9430), we demonstrate real-world applicability through downstream task evaluation. Object detection using YOLOv8 shows restored images achieve 63.0% mAP@0.5, significantly outperforming JPEG-compressed images at 49.0% mAP while maintaining the same compression ratio—a 14.0 percentage point improvement with 77.8% retention of original performance. Zero-shot cross-dataset evaluation demonstrates strong generalization: the pipeline trained on Semantic Riverscapes achieves 89.94% PSNR retention and 85.06% detection performance retention on VisDrone2019-DET without model retraining. Computational analysis confirms real-time processing capability (330 ms per image) with peak memory within acceptable limits (1.2–1.3 GB) for modern UAV platforms, alongside 2.5× increased onboard storage capacity. The proposed pipeline effectively addresses the bandwidth-quality trade-off, providing transmission efficiency and semantic information preservation essential for mission-critical UAV applications. 

Received: 30 November 2025 | Revised: 16 March 2026 | Accepted: 27 May 2026

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The data that support the findings of this study are openly available. The Semantic Riverscapes dataset is available in Landscape and Urban Planning at https://doi.org/10.1016/j.landurbplan.2022.104569, in reference [39], and the VisDrone2019-DET dataset is available in the 2019 IEEE/CVFICCV Workshop Proceedings at https://doi.org/10.1109/ICCVW.2019.00030, in reference [27]. 

Author Contribution Statement

F. M Abir Hossain: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization. Noman Saffat Sajid: Conceptualization, Methodology, Software, Investigation, Writing – original draft. Rashedur M. Rahman: Supervision, Project administration.