A Review of No-Reference Quality Assessment for Hyperspectral Sharpening
2023 11th International Conference on Information Systems and Computing Technology (ISCTech)(2023)
Abstract
Hyperspectral sharpening has developed rapidly in recent years. However, due to the lack of the ideal reference image, few studies conduct no-reference quality assessment for hyperspectral sharpening. Currently there is no recognized no-reference evaluation methods, which mainly focus on the reduced resolution assessment based on the spatial degradation strategy. This paper is the first to review two state-of-the-art no-reference quality assessment methods, namely MVG and QNR+. Since they both originate from quality assessment for the multispectral sharpening, we adapt them with band allocation to assess the quality of hyperspectral sharpening. We select 12 hyperspectral sharpening methods for evaluation experiments on Pavia University dataset. In addition, five reduced resolution assessing indexes and subjective analysis are used to verify the results of the no-reference evaluation. From the experimental results, we draw the conclusion that MVG and QNR+ have the potential to evaluate hyperspectral sharpening. Furthermore, we point out the pros and cons of the two no-reference assessment methods.
MoreTranslated text
Key words
quality assessment,no-reference,hyperspectral sharpening
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined