• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

一种基于图的超像素分割方法在图像融合中的应用

A Graph-Based Superpixel Segmentation Approach Applied to Pansharpening.

作者信息

Hallabia Hind

机构信息

UMR CNRS 7347-Materiaux, Microéléctronique, Acoustique, Nanotechnologies (GREMAN), Institut Universitaire de Technologie de Blois (IUT Blois), Tours University, 37000 Tours, France.

Institut National des Sciences Appliquées Centre-Val de Loire (INSA CVL Campus Blois), 41000 Blois, France.

出版信息

Sensors (Basel). 2025 Aug 12;25(16):4992. doi: 10.3390/s25164992.

DOI:10.3390/s25164992
PMID:40871856
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12390260/
Abstract

In this paper, an image-driven regional pansharpening technique based on simplex optimization analysis with a graph-based superpixel segmentation strategy is proposed. This fusion approach optimally combines spatial information derived from a high-resolution panchromatic (PAN) image and spectral information captured from a low-resolution multispectral (MS) image to generate a unique comprehensive high-resolution MS image. As the performance of such a fusion method relies on the choice of the fusion strategy, and in particular, on the way the algorithm is used for estimating gain coefficients, our proposal is dedicated to computing the injection gains over a graph-driven segmentation map. The graph-based segments are obtained by applying simple linear iterative clustering (SLIC) on the MS image followed by a region adjacency graph (RAG) merging stage. This graphical representation of the segmentation map is used as guidance for spatial information to be injected during fusion processing. The high-resolution MS image is achieved by inferring locally the details in accordance with the local simplex injection fusion rule. The quality improvements achievable by our proposal are evaluated and validated at reduced and at full scales using two high resolution datasets collected by GeoEye-1 and WorldView-3 sensors.

摘要

本文提出了一种基于单形优化分析和基于图的超像素分割策略的图像驱动区域全色锐化技术。这种融合方法将高分辨率全色（PAN）图像中的空间信息与低分辨率多光谱（MS）图像中获取的光谱信息进行最优组合，以生成独特的高分辨率综合MS图像。由于这种融合方法的性能依赖于融合策略的选择，特别是算法用于估计增益系数的方式，我们的方案致力于在基于图的分割图上计算注入增益。通过对MS图像应用简单线性迭代聚类（SLIC），然后进行区域邻接图（RAG）合并阶段，获得基于图的分割。这种分割图的图形表示用作融合处理期间注入空间信息的指导。通过根据局部单形注入融合规则局部推断细节来获得高分辨率MS图像。使用由GeoEye-1和WorldView-3传感器收集的两个高分辨率数据集，在缩小和全尺寸下评估和验证了我们方案可实现的质量改进。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/e4ad4e305c86/sensors-25-04992-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/9f731c685db9/sensors-25-04992-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/6332ef49c441/sensors-25-04992-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/4dc6b80c7d66/sensors-25-04992-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/e51e5372e65e/sensors-25-04992-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/44bdefcb62a8/sensors-25-04992-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/dc0a7e39d422/sensors-25-04992-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/0b763ed42546/sensors-25-04992-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/5a2c2155d3f8/sensors-25-04992-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/c048f3a57dc5/sensors-25-04992-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/e4ad4e305c86/sensors-25-04992-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/9f731c685db9/sensors-25-04992-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/6332ef49c441/sensors-25-04992-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/4dc6b80c7d66/sensors-25-04992-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/e51e5372e65e/sensors-25-04992-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/44bdefcb62a8/sensors-25-04992-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/dc0a7e39d422/sensors-25-04992-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/0b763ed42546/sensors-25-04992-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/5a2c2155d3f8/sensors-25-04992-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/c048f3a57dc5/sensors-25-04992-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/ad83/12390260/e4ad4e305c86/sensors-25-04992-g008.jpg

相似文献

1
A Graph-Based Superpixel Segmentation Approach Applied to Pansharpening.一种基于图的超像素分割方法在图像融合中的应用
Sensors (Basel). 2025 Aug 12;25(16):4992. doi: 10.3390/s25164992.
2
Prescription of Controlled Substances: Benefits and Risks管制药品的处方：益处与风险
3
Influence of early through late fusion on pancreas segmentation from imperfectly registered multimodal magnetic resonance imaging.早期至晚期融合对来自配准不完善的多模态磁共振成像的胰腺分割的影响。
J Med Imaging (Bellingham). 2025 Mar;12(2):024008. doi: 10.1117/1.JMI.12.2.024008. Epub 2025 Apr 26.
4
A novel pansharpening method based on side window filter and new injection gain matrices.一种基于侧窗滤波器和新型注入增益矩阵的新型全色锐化方法。
Sci Rep. 2025 Jul 18;15(1):26052. doi: 10.1038/s41598-025-08929-9.
5
A superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images.一种基于超像素的自注意力网络，用于高强度聚焦超声引导图像中的子宫肌瘤分割。
Sci Rep. 2025 Jul 1;15(1):21970. doi: 10.1038/s41598-025-08711-x.
6
Electrophoresis电泳
7
CDFAN: Cross-Domain Fusion Attention Network for Pansharpening.CDFAN：用于图像锐化的跨域融合注意力网络。
Entropy (Basel). 2025 May 27;27(6):567. doi: 10.3390/e27060567.
8
Short-Term Memory Impairment短期记忆障碍
9
Comparison of Two Modern Survival Prediction Tools, SORG-MLA and METSSS, in Patients With Symptomatic Long-bone Metastases Who Underwent Local Treatment With Surgery Followed by Radiotherapy and With Radiotherapy Alone.两种现代生存预测工具 SORG-MLA 和 METSSS 在接受手术联合放疗和单纯放疗治疗有症状长骨转移患者中的比较。
Clin Orthop Relat Res. 2024 Dec 1;482(12):2193-2208. doi: 10.1097/CORR.0000000000003185. Epub 2024 Jul 23.
10
MarkVCID cerebral small vessel consortium: I. Enrollment, clinical, fluid protocols.马克 VCID 脑小血管联盟：一、入组、临床、液体方案。
Alzheimers Dement. 2021 Apr;17(4):704-715. doi: 10.1002/alz.12215. Epub 2021 Jan 21.

本文引用的文献

1
Benchmarking of Multispectral Pansharpening: Reproducibility, Assessment, and Meta-Analysis.多光谱全色锐化的基准测试：可重复性、评估与荟萃分析
J Imaging. 2024 Dec 24;11(1):1. doi: 10.3390/jimaging11010001.
2
Full Scale Regression-Based Injection Coefficients for Panchromatic Sharpening.全尺度基于回归的多光谱锐化注入系数。
IEEE Trans Image Process. 2018 Jul;27(7):3418-3431. doi: 10.1109/TIP.2018.2819501.
3
Fusion of Multispectral and Panchromatic Images Based on Morphological Operators.基于形态学算子的多光谱与全色图像融合
IEEE Trans Image Process. 2016 Jun;25(6):2882-2895. doi: 10.1109/TIP.2016.2556944. Epub 2016 Apr 20.
4
Graph-Driven Diffusion and Random Walk Schemes for Image Segmentation.用于图像分割的基于图的扩散和随机游走算法
IEEE Trans Image Process. 2017 Jan;26(1):35-50. doi: 10.1109/TIP.2016.2621663. Epub 2016 Oct 26.
5
A New Pansharpening Method Based on Spatial and Spectral Sparsity Priors.一种基于空间和光谱稀疏先验的新型全色锐化方法。
IEEE Trans Image Process. 2014 Sep;23(9):4160-4174. doi: 10.1109/TIP.2014.2333661. Epub 2014 Jun 27.
6
SLIC superpixels compared to state-of-the-art superpixel methods.SLIC 超像素与最先进的超像素方法比较。
IEEE Trans Pattern Anal Mach Intell. 2012 Nov;34(11):2274-82. doi: 10.1109/TPAMI.2012.120.
7
Image quality assessment: from error visibility to structural similarity.图像质量评估：从误差可见性到结构相似性。
IEEE Trans Image Process. 2004 Apr;13(4):600-12. doi: 10.1109/tip.2003.819861.