排序方式： 共有4条查询结果，搜索用时 122 毫秒
1
1.
针对传统的遥感图像融合方法通常会引起光谱失真的问题和大多数基于深度学习的融合方法忽略充分利用每个卷积层信息的不足,本文结合密集连接卷积网络和残差网络的特性,提出了一个新的融合网络。该网络通过建立多个密集卷积块来充分利用卷积层的分级特征,同时块与块之间通过过渡层加快信息流动,从而最大程度地对特征进行极致利用并提取到丰富的特征。该网络应用残差学习拟合深层特征与浅层特征之间的残差,加快网络的收敛速度。实验中利用GaoFen-1（GF-1）和WorldView-2/3（WV-2/3）的多光谱图像MS （Multispectral Image）和全色图像PAN（Panchromatic Image）（MS与PAN的空间分辨率之比为4）评估本文提出方法的有效性。从视觉效果和定量评估结果两个方面来看,本文方法得到的融合结果要优于所对比的传统方法和深度学习方法,并且该网络具有鲁棒性,能够泛化到不需要预训练的其他卫星图像。本文方法通过特征的重复利用实现了光谱信息的高保真并提高了空间细节分辨能力,有利于遥感图像的应用研究。 相似文献
2.
In this paper, a pan-sharpening method, using non-subsampled contourlet transform (NSCT) and the theory of compressive sensing (CS), is proposed. The NSCT is used for sparse image representation to perform a multiscale and directional decomposition of source images in order to express their detail and express the sparsity of their high frequency. The CS is used to merge the multispectral (MS) and panchromatic (pan) images from partial random measurements. Two different fusion rules are then applied. The final pan-sharpened image is obtained by inverse NSCT. Experimental results show the efficiency of the proposed method, compared with pan sharpening based on standard NSCT, in terms of visual quality and objective assessment. Moreover, the proposed technique is very effective when the storage and transmission bandwidth are limited. 相似文献
3.
Optical remote sensing satellites obtain MS and Pan images simultaneously over the same coverage area. Remote sensing and image processing communities are working on different pan-sharpening methods capable of taking advantage of MS and Pan images. Each remote sensing system has its own advantages and disadvantages, leading to the question ‘Which pan-sharpening method should be used for which type of imagery?’ The aim of this research is to investigate the pan-sharpening performance of PLÉIADES-1A images. For this purpose, pan-sharpened images were generated using PCA, IHS and Brovey Transform which are the most popular pan-sharpening methods. Then, the pan-sharpened images were evaluated quantitatively using Correlation Coefficient, Root Mean Square Error, Relative Average Spectral Error, Spectral Angle Mapper and Erreur Relative Globale Adimensionnelle de Synthése. In addition, pan-sharpened images were evaluated qualitatively by taking object availability and completeness into consideration. 相似文献
4.
IKONOS图像的线性回归波段拟合融合方法 总被引：1，自引：0，他引：1
讨论基于线性回归波段拟合的空间细节信息提取方法的可行性。首先通过全色与多光谱图像构造线性回归方程,根据全色图像的高频成分设置最小二乘求解的权系数,然后利用回归系数构造低分辨率的全色图像,提取空间细节信息,最后将空间细节注入多光谱图像中进行融合。通过IKONOS全色和多光谱图像的融合实验,比较了本文方法与基于光谱响应函数的方法,结果表明:采用本文方法提取的空间细节信息进行融合,能达到甚至超过基于光谱响应函数方法的融合质量;相对于与FastIHS融合方法,本文方法的融合质量也有较大的提高。 相似文献
1