Image transformation based change detection technique is one kind of the most important techniques for multispectral images . traditional image transformation methods are based on orthodoxy theory , which might be difficult in deal with higher order dependences in multitemporal images 图像变换是实现多光谱遥感图像变化检测的一类重要方法,现有变化检测所使用的图像变换方法基本上都是基于正交变换,难以处理图像间的高阶相关信息。
In this paper , integrating with gis , gps technology and groud survey data , multi - source remote sensing data , including multispectral tm / etm + data , high spatial resolution spot 5 pan data and sar data were used to monitor the forest change in zhangpu county 本文利用常规的多光谱数据tm etm +数据、高空间分辨率spot5全色波段数据和合成孔径雷达数据，结合gis 、 gps技术和森林资源地面调查技术，对漳浦县森林资源展开遥感动态变化监测。
Afterwards , in order to decrease the contradiction between the more complex and mass remote sensing image data and relatively slow speed of information extraction , an improved sfim image fusion method is proposed . this modified algorithm is on the base of sfim fusion technique , combines ihs method and sfim method and then replaces the former mean filter by an adaptive weighted mean filter . compared with the results of several common fusion techniques through a set of simulation tests between multispectral images and panchromatic images , it is proved that the new method can get an excellent result for the aim of improving spatial resolution while preserving the spectral information of multispectral images 论文的主要工作和成果包括：在像素层，论文研究了多传感器数据融合理论及遥感图像预处理的过程和步骤，归纳了多源遥感图像像素层融合的常用算法，并针对目前遥感数据呈海量化、复杂化这一发展趋势同遥感信息提取的能力和效率滞后这一矛盾，在sfim算法的基础上，将ihs变换与sfim相结合，将原算法中的均值滤波器改进为自适应加权均值滤波器，提出了一种改进的sfim算法，通过对一组多光谱图像和全色图像的双传感器融合仿真对比试验，证明了该算法在保持原多光谱图像光谱信息的同时，能够有效提高融合图像的空间分辨能力。
In current remote sensing technology used in water resource monitoring , one multispectral tm image is often used , the resolution of tm image is low , in order to improve image and monitoring quality , we can use image fusion technique to fuse multispectral tm image and high resolution spot pan image of the same water area to get a new image has both high resolution and multispectral characteristics , so as to improve the monitor quality and the usage of images 在目前的水质遥感监测应用中，大多采用单幅tm图像数据，虽然图像具有多光谱性质，但空间分辨率较低，不利于提高监测精度。将多光谱tm图像与同水域高分辨率spot图像进行融合处理，得到一幅同时具有高光谱与高分辨率特性的图像，可以提高水质分类精度和遥感图像的利用率，这是本文研究工作的目的与意义。
The experiment results from practical multispectral images have shown that this algorithm is efficient . if the original image is reconstructed by five eigen subimages , the nearlossless compression ratio is above 11 for the data used in this paper and the psnr is more than 45db 实验结果表明，对机载64波段多光谱遥感图像进行k - l变换和整数小波变换后，选用五个本征子图像重建原图像，压缩比可以达到11以上，峰值信噪比则超过45db ，取得了其它方法无法获得的效果。
Secondly klt and reversible integer - to - integer wavelet transform for image compression are discussed , and a method of nearlossless compression of multispectral images is given , which combines klt and integer wavelet transform together . the spatial redundancy in the images is removed by klt and the inter - band redundancy is removed by the integer - to - integer wavelet transform 接着详细研究了k - l变换原理和整型小波的构造方法，编程实现了结合k - l变换和整数小波变换的多光谱图像压缩算法，该算法将k - l变换用于去除多光谱遥感图像的谱间冗余，在谱内则使用整型小波方法去除空间冗余。
Multispectral data for bathymetry is often performed in relatively clear shallow waters , up to now , no one use multispectral data for bathymetry in estuary waters of yellow river , where the highest sediment concentration in the world has been observed . in another part of this thesis , multispectral data acquired by landsat - 5 tm and in situ data are used for bathymetry in estuarine waters of yellow river . statistical models based on one band and two bands of tm respectively are developed 利用两期水深的比对可以揭示黄河水下三角洲的冲淤演变规律，但由于实测水深资料获取较为困难，因而利用遥感来反演水深是一个重要的选择，为此，本文在黄河口海现代黄河三角洲冲淤演变规律与遥感应用研究端走取两个试验区进行了多光谱遥感水深反演试验，试验结果表明，在极高泥沙浓度、较强水动力条件的黄河口海域，用多光谱遥感反演水深是可行的。
In this thesis , several issues concerning the machine learning and the classification of high dimensional multispectral data with limited training samples are addressed , which are based on statistic learning theory ( slt ) , support vector machine ( svm ) and artificial neural networks ( ann ) . the mai n work and results are outlined as follows : 1 . the characteristics of high dimensional multispectral data are studied , and the difficulties that deteriorate the performance of the traditional pattern classification algorithms are carefully analyzed 以统计学习理论( statisticlearningtheory ? slt ) 、支持向量机( supportvectormachine ? svm )和人工神经网络( artificialneuralnetworks ? ann )为基础，本文开展了以下几个方面的研究工作：深入分析了高维多光谱数据的特点和传统模式分类方法在高维多光谱数据分类中面临的困难。
By in - depth research of image texture and its application in multispectral image fusion , significant central coefficient ( scc ) algorithm based on redundant wavelet texture is proposed and its performance is tested to be also superior to the congeneric algorithms in the way of enhancing fusion quality 通过对图象纹理及其在多光谱图象融合中作用的深入研究，作者又提出了一种基于冗余小波纹理特征的重要中心系数( scc )融合算法，通过与其它同类融合算法结果的比较证明了该算法在提高融合结果质量上的先进性。
Applying statistic learning theory and support vector machine in high dimensional multispectral data classification , the hughes phenomenon is mitigated and higher classification accuracy is obtained . the relation between the performance of svm and kernel function , support vector , training set , data dimension and so on is studied . 2 深入研究了在高维多光谱数据分类中， svm的性能与核函数类型、核函数参数、支持向量( supportvector ? sv ) 、训练样本数目、数据维数等之间的关系。
