新无参考图像锐度评估方法，专为卫星影像设计。
A Novel No-Reference Image Quality Metric For Assessing Sharpness In Satellite Imagery
- 通过边缘梯度衰减率衡量图像锐度，无需参考图
- 在多种光照、噪声条件下仍与人眼感知高度一致
- 计算高效，适合大规模卫星影像质量监控
本研究提出一种新型无参考图像质量度量方法，用于评估图像锐度。该方法对噪声、曝光、对比度及图像内容变化具有鲁棒性，通过测量显著边缘上梯度的归一化衰减率，提供一种无需参考图像的客观锐度评估手段。主要面向卫星影像，旨在匹配人类视觉对锐度的感知，支持卫星机群的监控与质量表征。在多种图像类型和运行条件下，该度量表现出与人眼感知高度一致的性能。相比传统指标，此启发式方法可实现从低到高锐度的有序评分，是一种可靠且通用的质量评估工具，无需依赖高质量或真实参考图像。此外，相较于深度学习分析，该方法计算效率更高，实现更快、更节省资源的锐度评估。
原文摘要 · Abstract (English)
This study introduces a novel no-reference image quality metric aimed at assessing image sharpness. Designed to be robust against variations in noise, exposure, contrast, and image content, it measures the normalized decay rate of gradients along pronounced edges, offering an objective method for sharpness evaluation without reference images. Primarily developed for satellite imagery to align with human visual perception of sharpness, this metric supports monitoring and quality characterization of satellite fleets. It demonstrates significant utility and superior performance in consistency with human perception across various image types and operational conditions. Unlike conventional metrics, this heuristic approach provides a way to score images from lower to higher sharpness, making it a reliable and versatile tool for enhancing quality assessment processes without the need for pristine or ground truth comparison. Additionally, this metric is computationally efficient compared to deep learning analysis, ensuring faster and more resource-effective sharpness evaluations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。