Assessing Full-Resolution Pansharpening Quality: A Comparative Study of Methods and Measurements

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Since the introduction of pansharpening, quality assessment has played a pivotal role in related remote sensing research to ensure the overall system's reliability. Full-resolution quality assessment is a debated research topic for applications. However, full-resolution (FR) assessment faces challenges due to the absence of reference compared to reduced-resolution assessment. Moreover, the lack of ground truth makes measuring quality metrics even more challenging. To summarize the current measures for these two challenges, this paper presents a comprehensive study of FR methods. We review various FR techniques and analyze how they extract spatial and spectral features from pansharpened images without reference to High-Resolution Multispectral (HR-MS) images. A classification approach is proposed to group these methods based on their shared characteristics, making it easier for researchers and practitioners to compare and select the most appropriate FR method for specific applications. Furthermore, we provide a summary of strategies for measuring FR performance in the absence of ground truth. These strategies are classified into subjective and objective approaches. Additionally, we conduct a board analysis on a large-scale public pansharpened database with unified measuring criteria. This unified analysis allows us to present experiments from a statistical perspective, measure FR protocols' performance, and provide a broad qualitative and quantitative analysis. Overall, this study contributes to the development of pansharpening and provides guidance for selecting appropriate FR methods, as well as strategies for measuring FR performance.
Funding Information
  • Major science and technology projects in Xinjiang Uygur Autonomous Region (2022A02012-2)
  • Natural Science Basic Research Plan in Shaanxi Province of China (2023-JC-JQ-51)
  • Xi'an Science and Technology Project (21RGZN0009)

This publication has 68 references indexed in Scilit: