| 基于有约束CNMF的遥感高光谱多光谱图像融合 |
| |
| 引用本文： | 刘洋,徐洪平,易航,施清平,夏伟强,康健.基于有约束CNMF的遥感高光谱多光谱图像融合[J].应用科学学报,2016,34(6):651-660. |
| |
| 作者姓名： | 刘洋 徐洪平 易航 施清平 夏伟强 康健 |
| |
| 作者单位： | 北京宇航系统工程研究所, 北京 100076 |
| |
| 摘 要： | 针对高光谱图像空间分辨率较低的问题，设计了一种基于光谱解混的高光谱、多光谱图像融合算法（VSC-CNMF）. 结合遥感图像的实际物理特性，在混合像元分解时加入端元单形体最小体积约束和丰度稀疏约束，通过光谱退化、空间退化和迭代解混，实现不同图像间端元和丰度的匹配，获得了具有高空间分辨率的融合图像. 仿真实验表明，VSC-CNMF可得到具有更高空间质量和光谱质量的融合图像.
|
| 关 键 词： | 最小体积约束 非负矩阵分解 图像融合 高光谱图像 稀疏约束 空间分辨率 |
| 收稿时间： | 2016-05-10 |
| 修稿时间： | 2016-06-20 |
Hyperspectral and Multi-spectral Data Fusion Based on Constraint CNMF |
| |
| LIU Yang,XU Hong-ping,YI Hang,SHI Qing-ping,XIA Wei-qiang,KANG Jian.Hyperspectral and Multi-spectral Data Fusion Based on Constraint CNMF[J].Journal of Applied Sciences,2016,34(6):651-660. |
| |
| Authors: | LIU Yang XU Hong-ping YI Hang SHI Qing-ping XIA Wei-qiang KANG Jian |
| |
| Institution: | Beijing Institute of Aerospace System Engineering, Beijing 100076, China |
| |
| Abstract: | Hyperspectral images generally have lowspatial resolution due to limitations of the imaging spectrometer. In this paper, VSC-CNMF is designed to produce a fused image from hyperspectral and multi-spectral images. An end-member smallest volume and abundance sparseness constrained NMF (VSC-CNMF) algorithm is proposed based on the physical characteristics of remote sensing images. We match the end-member and abundance of two types of images by spectral and spatial degradations, and get the fused image with high spatial and spectral resolution according to some un-mixing update rules. Simulation results show that fused images with higher spatial and spectral quality can be obtained with VSC-CNMF. |
| |
| Keywords: | non-negative matrix factorization hyperspectral image sparseness constraint spatial resolution minimum volume constraint image fusion |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《应用科学学报》浏览原始摘要信息 |
| 点击此处可从《应用科学学报》下载免费的PDF全文 |
|
