BP神经网络在多源图像融合中的应用研究

采用BP神经网络与SVR融合法相结合的方法来实现像素级多源图像融合。改进型的SVR方法,用来进行全色波段和多光谱波段的融合。首先将各多光谱波段与全色波段求算回归系数,然后利用回归系数与多光谱波段合成模拟高空间分辨率全色波段,最后利用比值变换完成各波段的融合．通过仿真证明,BPNN—SVR融合法优于SVR融合法。     

基于小波变换的全色多光谱高空间图像数据双源融合算法处理技术研究

针对多光谱图像传感器数据与全色图像传感器数据进行了双源融合算法研究.在对现有的各种融合算法进行详细的归纳和总结的基础上,利用多光谱图像高光谱信息与全色图像高空间信息两者之间的互补性,研究了在尽可能保留原光谱信息的前提下,提高空间分辨率的像素级图像融合算法,并对多传感器遥感图像进行了仿真实验研究.     

土地覆盖分类影像融合与精度评价研究

影像融合技术可以使遥感影像具有高光谱和高空间分辨率的效果,实现不同空间、光谱、时间等多种分辨率的信息资源互补,从而提高图像的空间分辨率,提高图像的几何精度.文章利用ERDAS软件,对遥感影像数据进行融合,采用乘积变换、PCA变换、Brocey变换、小波变换等遥感影像融合方法对多光谱与全色影像进行融合和土地覆盖分类研究.通过结合图像的光谱统计参数和融合图像的分类精度,对这些方法的分类精度进行评价.这4种方法对于原始影像分类精度,均有不同程度的提高.而小波变换所得融合影像与原多光谱影像的相关系数最大,均方差、平均梯度和信息熵最大,偏差指数最小,影像所含信息量最多;在光谱特性、图像清晰度、对于空间细节信息的表现能力上其它三种方法都好,所得融合影像的分类精度也是最高的.小波变换更适合融合影像的土地覆盖分类研究.     

基于成像机理的遥感图像融合

探讨了遥感多光谱与全色波段图像的融合问题．分析了多光谱与全色波段成像机理,提出了一种新的基于小波变换的遥感图像融合方法,实验结果表明,该方法可有效综合多光谱与全色波段图像的优点,从而获得具有较高空间分辨率的多谱图像．     

结合最优亮度分量的遥感图像融合方法

针对基于亮度色调饱和度变换的遥感图像融合方法中存在的光谱损失问题,提出了一种结合最优亮度分量的融合方法．根据全色图像的亮度分量,利用克隆选择算法给出每幅单光谱图像对应的全局优化权值,该权值可反映出每幅单光谱图像相对于全色图像亮度分量中所占的折中比例,从而减弱了单光谱图像间的相关性,可获得更加逼近全色图像的亮度分量;利用最优亮度分量在改进的空间分辨率增加(ARSIS)框架下获取具有高分辨率的多光谱图像．算法针对快鸟卫星图像数据的实验结果,验证了新方法在降低光谱损失和增强融合图像细节信息方面的有效性,所获得的融合后的高分辨率多光谱图像具有较小的光谱损失．     

WorldView-2遥感图像融合新方法

新型高分辨率WorldView-2星载图像的出现给现有的图像融合技术带来了更大的挑战,该文提出了一种全色光和多光谱图像融合新方法。首先采用最近邻插值对多光谱图像重采样放大;然后结合WorldView-2各波段光谱响应特点利用多元线性回归构造出低分辨率全色光图像,通过对原始高分辨率全色光图像空间细节信息的提取并将其注入至多光谱图像的成分空间中;最后经对应分析反变换得到融合结果。实验结果表明,该方法在融合WorldView-2遥感图像时能够在提高空间分辨率和保持光谱信息两方面达到较好的平衡,优于现有的几种融合方法。     

新型高光谱图像的超分辨率制图方法

由于高光谱图像的应用在很大程度上受限于其较低的空间分辨率,为此提出了一种结合支持向量机和小波变换的高光谱图像超分辨率制图方法．先对高光谱图像进行光谱解混得到分量图,然后对分量图进行一级小波分解．各局域窗内中心像元的3个高频系数与邻域像元低频系数之间的对应关系表示为训练样本,用于支持向量机的学习．训练好的模型用来对低分辨率图像即分量图进行超分辨率制图．实验表明,这种借助小波变换来获取训练样本的学习方法无需先验信息,相比采用BP神经网络学习的方法,支持向量机的超分辨率制图效果更佳．     

非下采样剪切波变换域下遥感图像融合

多光谱图像与全色图像的融合已被广泛应用于提高后续图像处理效果以满足图像进一步应用的需要,本文提出了一种在非下采样剪切波变换域中基于区域清晰度加权和导向滤波相结合的遥感图像融合方法.利用剪切波变换将多光谱图像的亮度分量与全色图像分别分解为低频子带和高频子带;针对高低频子带的特点分别设计高低频子带融合规则;对融合系数取剪切...     

基于NSCT和PCA变换域的遥感图像融合算法

为使融合后的图像在尽可能保持原图像光谱信息的同时,有效提高空间细节信息,提出了一种新的基于非下采样Contourlet变换（NSCT）和主成分分析（PCA）的全色图像和多光谱图像融合算法.对多光谱图像进行PCA变换得到主元分量,将处理后的主元分量与全色图像进行NSCT分解,针对低频子带系数选择提出了一种基于窗口与局部方差相结合的融合策略;在高频子带系数选择上,提出了基于区域线性相关测定的融合策略.进行非下采样Contourlet逆变换和PCA逆变换,得到具有高空间质量的多光谱图像.实验结果表明,提出的算法在保留光谱信息和提高空间细节信息的综合性能上有所提高,能够取得较好的融合效果.     

基于双正交小波遥感图像融合及效果评价

将双正交小波变换与IHS变换相结合,使得融合图像最大限度地保留了多光谱影像的光谱信息,同时提高了图像的清晰度和空间分辨率.文中给出了ETM＋影像多光谱与全色融合结果,用双正交与Db4I、HS法进行了比较,结果表明无论是目视解译还是定量分析,双正交融合方法均优于后两者.实验分析表明,基于双正交小波遥感图像数据融合技术是提高多源遥感影像表现能力的一种重要方法.     

Fusion of multi-spectral image and panchromatic image based on support vector regression

In our study,support vector value contourlet transform is constructed by using support vector regression model and directional filter banks.The transform is then used to decompose source images at multi-scale,multi-direction and multi-resolution.After that,the super-resolved multi-spectral image is reconstructed by utilizing the strong learning ability of support vector regression and the correlation between multi-spectral image and panchromatic image.Finally,the super-resolved multi-spectral image and the panchromatic image are fused based on regions at different levels.Our experiments show that,the learning method based on support vector regression can improve the effect of super-resolution of multi-spectral image.The fused image preserves both high space resolution and spectrum information of multi-spectral image.     

Remote sensing image fusion based on sparse non-negative matrix factorization

In order to reduce the spectral and spatial distortions, a novel method based on sparse non-negative matrix factorization (SNMF) is proposed for multispectral and panchromatic images fusion. Firstly, the high spatial resolution and low spatial resolution dictionaries are learned from panchromatic. Then we construct a sparse non-negative matrix factorization model of the multispectral image. Thus, the coefficients matrix with spectral information can be obtained. The high spatial resolution multispectral image is produced by the multiplication high spatial resolution dictionary and the coefficients matrix. By introducing the sparse regularization, the instability of the standard non-negative matrix factorization is conquered and the fused image can preserve the high spectral and spatial information. Some experiments are made on QuickBird and Geoeye satellite datasets, and experimental results show that our proposed method can reduce distortions in both the spectral and spatial domains, and outperform some related pan-sharpening approaches in visual results and numerical guidelines.     

Application of remote-sensing-image fusion to the monitoring of mining induced subsidence

We discuss remote-sensing-image fusion based on a multi-band wavelet and RGB feature fusion method. The fused data can be used to monitor the dynamic evolution of mining induced subsidence. High resolution panchromatic image data and multi-spectral image data were first decomposed with a multi-ary wavelet method. Then the high frequency components of the high resolution image were fused with the features from the R, G, B bands of the multi-spectral image to form a new high frequency component. Then the newly formed high frequency component and the low frequency component were inversely transformed using a multi-ary wavelet method. Finally, color images were formed from the newly formed R, G, B bands. In our experiment we used images with a resolution of 10 m (SPOT), and TM30 images, of the Huainan mining area. These images were fused with a trinary wavelet method. In addition, we used four indexes-entropy, average gradient, wavelet energy and spectral distortion-to assess the new method. The result indicates that this new method can improve the clarity and resolution of the images and also preserves the information from the original images. Using the fused images for monitoring mining induced subsidence achieves a good effect.     

Fusion of multispectral image and panchromatic image based on NSCT and NMF

A novel fusion method of multispectral image and panchromatic image based on nonsubsampled contourlet transform(NSCT) and non-negative matrix factorization(NMF) is presented,the aim of which is to preserve both spectral and spatial information simultaneously in fused image.NMF is a matrix factorization method,which can extract the local feature by choosing suitable dimension of the feature subspace.Firstly the multispectral image was represented in intensity hue saturation(IHS) system.Then the I component and panchromatic image were decomposed by NSCT.Next we used NMF to learn the feature of both multispectral and panchromatic images’ low-frequency subbands,and the selection principle of the other coefficients was absolute maximum criterion.Finally the new coefficients were reconstructed to get the fused image.Experiments are carried out and the results are compared with some other methods,which show that the new method performs better in improving the spatial resolution and preserving the feature information than the other existing relative methods.     

基于小波包移频算法的遥感图像融合技术

为了对分类最小二乘支持向量机实施有效的稀疏化，以提高分类速率，采用分类相关分析算法，按序提取样本核矩阵的全部分类相关成分，并依据样本核矩阵各列与分类相关成分的相关性，对训练集所有个体按分类的重要性排序，进而可选取最重要的部分个体作为支持向量，并将其余非支持向量的信息转移至支持向量，以提高支持向量的分类表达能力.由此构建一种新的稀疏型最小二乘支持向量机CS LSSVM，并将其应用于多个模式分类的实际问题.测试结果表明，CS LSSVM稀疏性很强，且保持了标准LSSVM的分类性能，还可直接适用于多类问题.     

基于PCA、SFIM、MLT算法的ETM+影像融合

采用PCA、SFIM和MLT3种融合算法对ETM 影像进行融合,并从融合影像的光谱质量、空间结构信息和分类精度等方面对融合方法进行评价.结果表明,SFIM融合法的光谱质量最高,PCA融合法具有最高的高频空间结构信息融入度,MLT融合法具有最高的分类精度,3种融合影像的分类精度都较原始影像的分类精度有所提高.     

ALOS全色与多光谱影像融合方法的比较研究

以浙江省德清县ALOS影像为基础数据,探讨了利用乘积法、高通滤波法、小波变换、HIS变换、Brovey变换、PCA变换、Gram-Schmidt变换等七种影像融合方法,对ALOS全色与多光谱影像进行融合,对各方法的融合结果进行了定性和定量分析.实验结果表明,Gram-Schmidt变换在保持多光谱影像光谱信息的同时,显著提高了融合影像的空间分辨率,是最适合ALOS全色与多光谱影像的融合方法,为ALOS影像应用提供了参考.